Criteria

Text:
Topic:
Display:

Results

Viewing 1 to 30 of 1041
2017-09-23
Technical Paper
2017-01-1971
Sihan Chen, Libo Huang, Xin Bi, Jie Bai
Abstract For sensing system, the trustworthiness of the variant sensors is the crucial point when dealing with advanced driving assistant system application. In this paper, an approach to a hybrid camera-radar application of vehicle tracking is presented, able to meet the requirement of such demand. Most of the time, different types of commercial sensors available nowadays specialize in different situations, such as the ability of offering a wealth of detailed information about the scene for the camera or the powerful resistance to the severe weather for the millimeter-wave (MMW) radar. The detection and tracking in different sensors are usually independent. Thus, the work here that combines the variant information provided by different sensors is indispensable and worthwhile. For the real-time requirement of merging the measurement of automotive MMW radar in high speed, this paper first proposes a fast vehicle tracking algorithm based on image perceptual hash encoding.
2017-09-23
Journal Article
2017-01-1969
Yuanxin Zhong, Sijia Wang, Shichao Xie, Zhong Cao, Kun Jiang, Diange Yang
Abstract Real-time reconstruction of 3D environment attributed with semantic information is significant for a variety of applications, such as obstacle detection, traffic scene comprehension and autonomous navigation. The current approaches to achieve it are mainly using stereo vision, Structure from Motion (SfM) or mobile LiDAR sensors. Each of these approaches has its own limitation, stereo vision has high computational cost, SfM needs accurate calibration between a sequences of images, and the onboard LiDAR sensor can only provide sparse points without color information. This paper describes a novel method for traffic scene semantic segmentation by combining sparse LiDAR point cloud (e.g. from Velodyne scans), with monocular color image. The key novelty of the method is the semantic coupling of stereoscopic point cloud with color lattice from camera image labelled through a Convolutional Neural Network (CNN).
2017-09-23
Technical Paper
2017-01-1975
Wenhui Li, Wenlan Li, Jialun Liu, Yuhao Chen
Abstract Vehicle detection has been a fundamental problem in the research of Intelligent Traffic System (ITS), especially in urban driving environment. Over the past decades, vision-based vehicle detection has got a considerable attention. In addition to the rich appearance information, the stereo vision method also provides depth information, which could achieve higher accuracy and precision. In this paper, a hybrid method for stereo vision-based real-time vehicle detection in urban environment is proposed. Firstly, we extract vehicle features and generate the Region of Interest (ROI). Semi-global Matching (SGM) algorithm is then utilized on the ROIs to generate disparity maps and get the depth information, which could be used to compute the width of each ROI. The noise regions, always with obvious depth variation in the disparity maps are excluded by the clustering approach.
2017-09-23
Technical Paper
2017-01-1977
Xin Bi, Bin Tan, Zhijun Xu, Libo Huang
Abstract Vehicle and pedestrian detection technology is the most important part of advanced driving assistance system (ADAS) and automatic driving. The fusion of millimeter wave radar and camera is an important trend to enhance the environmental perception performance. In this paper, we propose a method of vehicle and pedestrian detection based on millimeter wave radar and camera. Moreover, the proposed method complete the detection of vehicle and pedestrian based on dynamic region generated by the radar data and sliding window. First, the radar target information is mapped to the image by means of coordinate transformation. Then by analyzing the scene, we obtain the sliding windows. Next, the sliding windows are detected by HOG features and SVM classifier in a rough detect. Then using the match function to confirm the target. Finally detecting the windows in a precision detection and merging the detecting windows.
2017-09-23
Technical Paper
2017-01-1978
Yuxiang Feng, Simon Pickering, Edward Chappell, Pejman iravani PhD, Chris Brace
Abstract The major contribution of this paper is to propose a low-cost accurate distance estimation approach. It can potentially be used in driver modelling, accident avoidance and autonomous driving. Based on MATLAB and Python, sensory data from a Continental radar and a monocular dashcam were fused using a Kalman filter. Both sensors were mounted on a Volkswagen Sharan, performing repeated driving on a same route. The established system consists of three components, radar data processing, camera data processing and data fusion using Kalman filter. For radar data processing, raw radar measurements were directly collected from a data logger and analyzed using a Python program. Valid data were extracted and time stamped for further use. Meanwhile, a Nextbase monocular dashcam was used to record corresponding traffic scenarios. In order to measure headway distance from these videos, object depicting the leading vehicle was first located in each frame.
2017-09-23
Technical Paper
2017-01-1997
Cui Hua
Abstract Vision based driving environment perception is current research hotspot in automatic driving field, which has made great progress due to the continuous breakthroughs in the research of deep neural network. As is well known, deep neural network has won tremendous successes in a wide variety of image recognition tasks, such as pedestrian detection and vehicle identification, which have accomplished the commercialization successfully in intelligent monitor system. Nevertheless, driving environment perception has a higher request for the generalization performance of deep neural network, which needs further studies on its design and training methods. In this paper, we presented a new boosted deep neural network in order to improve its generalization performance and meanwhile keep computational budget constant. Above all, the most representative methods to improve the generalization performance of deep neural network were introduced.
2017-09-23
Technical Paper
2017-01-1998
Shun Yang, Weiwen Deng, Zhenyi Liu, Ying Wang
Abstract Intelligent driving, aimed for collision avoidance and self-navigation, is mainly based on environmental sensing via radar, lidar and/or camera. While each of the sensors has its own unique pros and cons, camera is especially good at object detection, recognition and tracking. However, unpredictable environmental illumination can potentially cause misdetection or false detection. To investigate the influence of illumination conditions on detection algorithms, we reproduced various illumination intensities in a photo-realistic virtual world, which leverages recent progress in computer graphics, and verified vehicle detection effect there. In the virtual world, the environmental illumination is controlled precisely from low to high to simulate different illumination conditions in the driving scenarios (with relative luminous intensity from 0.01 to 400). Sedan cars with different colors are modelled in the virtual world and used for detection task.
2017-09-19
Technical Paper
2017-01-2048
Bryan Shambaugh, Patrick Browning
This paper investigates the effect of various magnetic field configurations on an ionized exhaust plume operating under near vacuum conditions. The purpose of this investigation is to determine if deploying a toroidal magnetic field around an ionized exhaust plume can alter the exhaust profile. The test apparatus utilizes a series of twelve N52 grade neodymium magnets mounted on a steel toroid. The design is proposed as a low-cost alternative to toroidal electromagnets. Five different apparatus configurations were tested in this experiment. Each test was documented using 12 sets of photographs taken from a fixed position with respect to the flow. Photographs were taken after the arc jet had run for 10, 20, and 30 seconds. Data from each configuration was compiled using image processing and compared with data from other configurations at corresponding time periods. Two configurations were run as control tests without any magnetic interference.
2017-09-19
Technical Paper
2017-01-2123
Violet Leavers
The need to maintain aircraft in remote, harsh environments poses significant challenges for on-site condition monitoring. For example, in desert assignments or on-board ships, frequent rotation of staff with variable levels of skill requires condition monitoring equipment that is not only robust and portable but also user friendly and requiring a minimum of training to set up and use correctly. The mainstays of any on-site aerospace maintenance program are various fluid and particulate condition monitoring tests that convey information about the current mechanical state of the system. In the front line of these is the collection and analysis of wear debris particles retrieved from a component’s lubricating or power transmission fluid or from magnetic plugs. It is standard practice within the specialist laboratory environment to view and image wear debris using a microscope.
2017-09-19
Journal Article
2017-01-2165
Christian Moeller, Hans Christian Schmidt, Philip Koch, Christian Boehlmann, Simon Kothe, Jörg Wollnack, Wolfgang Hintze
The high demand of efficient large scale machining operations by concurrently decreasing operating time and costs has led to an increasing usage of industrial robots in contrast to large scaled machining centers. The main disadvantage of industrial robots used for machining processes is their poor absolute accuracy, caused by the serial construction, resilience of gearings and sensitivity for temperature changes. Additionally high process forces that occur during machining of CFRP structures in aerospace industry lead to significant path errors due to low structural stiffness of the robot kinematic. These errors cannot be detected by means of motor encoders. That is why calibration processes and internal control laws have no effect on errors caused by elastic deformation. In this research paper an approach for increasing the absolute accuracy of an industrial milling robot with help of a laser tracker system during machining tasks will be presented.
2017-09-04
Technical Paper
2017-24-0046
Richard Stone, Ben Williams, Paul Ewart
Abstract The increased efficiency and specific output with Gasoline Direct Injection (GDI) engines are well known, but so too are the higher levels of Particulate Matter emissions compared with Port Fuel Injection (PFI) engines. To minimise Particulate Matter emissions, then it is necessary to understand and control the mixture preparation process, and important insights into GDI engine mixture preparation and combustion can be obtained from optical access engines. Such data is also crucial for validating models that predict flows, sprays and air fuel ratio distributions. The purpose of this paper is to review a number of optical techniques; the interpretation of the results is engine specific so will not be covered here. Mie scattering can be used for semi-quantitative measurements of the fuel spray and this can be followed with Planar Laser Induced Fluorescence (PLIF) for determining the air fuel ratio and temperature distributions.
2017-09-04
Technical Paper
2017-24-0126
Christian Zöllner, Dieter Brueggemann
Abstract The removal of particulate matter (PM) from diesel exhaust is necessary to protect the environment and human health. To meet the strict emission standards for diesel engines an additional exhaust aftertreatment system is essential. Diesel particulate filters (DPF) are established devices to remove emitted PM from diesel exhaust. But the deposition and the accumulation of soot in the DPF influence the filter back pressure and therefore the engine performance and the fuel consumption. Thus a periodical regeneration through PM oxidation is necessary. The oxidation behavior should result in an effective regeneration mode that minimizes the fuel penalty and limits the temperature rise while maintaining a high regeneration efficiency. Excessive and fast regenerations have to be avoided as well as uncontrolled oxidations, which may lead to damages of the filter and fuel penalty.
2017-09-04
Journal Article
2017-24-0109
Nic Van Vuuren, Lucio Postrioti, Gabriele Brizi, Federico Picchiotti
Selective Catalytic Reduction (SCR) diesel exhaust aftertreatment systems are virtually indispensable to meet NOx emissions limits worldwide. These systems generate the NH3 reductant by injecting aqueous urea solution (AUS-32/AdBlue®/DEF) into the exhaust for the SCR NOx reduction reactions. Understanding the AUS-32 injector spray performance is critical to proper optimization of the SCR system. Specifically, better knowledge is required of urea sprays under operating conditions including those where fluid temperatures exceed the atmospheric fluid boiling point. Results were previously presented from imaging of an AUS-32 injector spray which showed substantial structural differences in the spray between room temperature fluid conditions, and conditions where the fluid temperature approached and exceeded 104° C and “flash boiling” of the fluid was initiated.
2017-06-05
Technical Paper
2017-01-1874
Tongyang Shi, Yangfan Liu, J Stuart Bolton, Frank Eberhardt, Warner Frazer
Abstract Wideband Acoustical Holography (WBH), which is a monopole-based, equivalent source procedure (J. Hald, “Wideband Acoustical Holography,” INTER-NOISE 2014), has proven to offer accurate noise source visualization results in experiments with a simple noise source: e.g., a loudspeaker (T. Shi, Y. Liu, J.S. Bolton, “The Use of Wideband Holography for Noise Source Visualization”, NOISE-CON 2016). From a previous study, it was found that the advantage of this procedure is the ability to optimize the solution in the case of an under-determined system: i.e., when the number of measurements is much smaller than the number of parameters that must be estimated in the model. In the present work, a diesel engine noise source was measured by using one set of measurements from a thirty-five channel combo-array placed in front of the engine.
2017-06-05
Technical Paper
2017-01-1872
Masao Nagamatsu
Abstract The almost current sound localization methods do not have enough resolution in low frequency sound localization. To overcome this disadvantage, I am now developing the new sound localization method, Double Nearfield Acoustic Holography (DNAH) method. This method is a converted method of conventional Nearfield Acoustic Holography (NAH) method. In this proposing method, the resolution of low frequency sound localization is improved by using sound propagation information on doubled measurement planes. To prove the performance of proposing method, the basic experiments with variable conditions are conducted. In these experiments, the small speakers are used as sound sources. In this paper, to discuss the ability to apply to actual industry, the effect of measurement distance from the sound source is explained. Some experimental results with changing measurement distance are shown in this paper.
2017-05-18
Journal Article
2017-01-9678
G Agawane, Varun Jadon, Venkatesham Balide, R Banerjee
Abstract Liquid sloshing noise from an automotive fuel tank is becoming increasingly important during frequent accelerating/decelerating driving conditions. It is becoming more apparent due to significant decrease in other noise sources in a vehicle, particularly in hybrid vehicles. As a step toward understanding the dynamics of liquid sloshing and noise generation mechanism, an experimental study was performed in a partially filled rectangular tank. A systematic study was performed to understand the effects of critical parameters like fill level and acceleration/deceleration magnitude. Response parameters like dynamic pressure, dynamic force, dynamic acceleration and sound pressure levels along with high speed video images were recorded. The proposed experimental setup was able to demonstrate major events leading to sloshing noise generation. These events in the sloshing mechanism have been analysed from the dynamic sensor data and correlated with high speed video images.
2017-03-28
Technical Paper
2017-01-0673
Alessandro Cimarello, Carlo N. Grimaldi, Francesco Mariani, Michele Battistoni, Massimo Dal Re
Abstract Radio Frequency Corona ignition systems represent an interesting solution among innovative ignition strategies for their ability to stabilize the combustion and to extend the engine operating range. The corona discharge, generated by a strong electric field at a frequency of about 1 MHz, produces the ignition of the air-fuel mixture in multiple spots, characterized by a large volume when compared to a conventional spark, increasing the early flame growth speed. The transient plasma generated by the discharge, by means of thermal, kinetic and transport effects, allows a robust initialization of the combustion even in critical conditions, such as using diluted or lean mixtures. In this work the effects of Corona ignition have been analyzed on a single cylinder optical engine fueled with gasoline, comparing the results with those of a traditional single spark ignition.
2017-03-28
Technical Paper
2017-01-0753
Marcus Olof Lundgren, Zhenkan Wang, Alexios Matamis, Oivind Andersson, Mattias Richter, Martin Tuner, Marcus Alden, Andersson Arne
Abstract Gasoline partially premixed combustion (PPC) has shown potential in terms of high efficiency with low emissions of oxides of nitrogen (NOx) and soot. Despite these benefits, emissions of unburned hydrocarbons (UHC) and carbon monoxide (CO) are the main shortcomings of the concept. These are caused, among other things, by overlean zones near the injector tip and injector dribble. Previous diesel low temperature combustion (LTC) research has demonstrated post injections to be an effective strategy to mitigate these emissions. The main objective of this work is to investigate the impact of post injections on CO and UHC emissions in a quiescent (non-swirling) combustion system. A blend of primary reference fuels, PRF87, having properties similar to US pump gasoline was used at PPC conditions in a heavy duty optical engine. The start of the main injection was maintained constant. Dwell and mass repartition between the main and post injections were varied to evaluate their effect.
2017-03-28
Technical Paper
2017-01-0755
Karthik Nithyanandan, Yongli Gao, Han Wu, Chia-Fon Lee, Fushui Liu, Junhao Yan
Abstract Dual-fuel combustion combining a premixed charge of compressed natural gas (CNG) and a pilot injection of diesel fuel offer the potential to reduce diesel fuel consumption and drastically reduce soot emissions. In this study, dual-fuel combustion using methane ignited with a pilot injection of No. 2 diesel fuel, was studied in a single cylinder diesel engine with optical access. Experiments were performed at a CNG substitution rate of 70% CNG (based on energy) over a wide range of equivalence ratios of the premixed charge, as well as different diesel injection strategies (single and double injection). A color high-speed camera was used in order to identify and distinguish between lean-premixed methane combustion and diffusion combustion in dual-fuel combustion. The effect of multiple diesel injections is also investigated optically as a means to enhance flame propagation towards the center of the combustion chamber.
2017-03-28
Technical Paper
2017-01-0573
Mohammed Jaasim Mubarak ali, Francisco Hernandez Perez, R Vallinayagam, S Vedharaj, Bengt Johansson, Hong Im
Abstract Full cycle simulations of KAUST optical diesel engine were conducted in order to provide insights into the details of fuel spray, mixing, and combustion characteristics at different start of injection (SOI) conditions. Although optical diagnostics provide valuable information, the high fidelity simulations with matched parametric conditions improve fundamental understanding of relevant physical and chemical processes by accessing additional observables such as the local mixture distribution, intermediate species concentrations, and detailed chemical reaction rates. Commercial software, CONVERGE™, was used as the main simulation tool, with the Reynolds averaged Navier-Stokes (RANS) turbulence model and the multi-zone (SAGE) combustion model to compute the chemical reaction terms. SOI is varied from late compression ignition (CI) to early partially premixed combustion (PPC) conditions.
2017-03-28
Technical Paper
2017-01-0262
Taewon Kim, Xi Luo, Mustafa Al-Sadoon, Ming-Chia Lai, Marcis Jansons, Doohyun Kim, Jason Martz, Angela Violi, Eric Gingrich
Abstract Three jet fuel surrogates were compared against their target fuels in a compression ignited optical engine under a range of start-of-injection temperatures and densities. The jet fuel surrogates are representative of petroleum-based Jet-A POSF-4658, natural gas-derived S-8 POSF-4734 and coal-derived Sasol IPK POSF-5642, and were prepared from a palette of n-dodecane, n-decane, decalin, toluene, iso-octane and iso-cetane. Optical chemiluminescence and liquid penetration length measurements as well as cylinder pressure-based combustion analyses were applied to examine fuel behavior during the injection and combustion process. HCHO* emissions obtained from broadband UV imaging were used as a marker for low temperature reactivity, while 309 nm narrow band filtered imaging was applied to identify the occurrence of OH*, autoignition and high temperature reactivity.
2017-03-28
Technical Paper
2017-01-0104
Maryam Moosaei, Yi Zhang, Ashley Micks, Simon Smith, Madeline J. Goh, Vidya Nariyambut Murali
Abstract In this work, we outline a process for traffic light detection in the context of autonomous vehicles and driver assistance technology features. For our approach, we leverage the automatic annotations from virtually generated data of road scenes. Using the automatically generated bounding boxes around the illuminated traffic lights themselves, we trained an 8-layer deep neural network, without pre-training, for classification of traffic light signals (green, amber, red). After training on virtual data, we tested the network on real world data collected from a forward facing camera on a vehicle. Our new region proposal technique uses color space conversion and contour extraction to identify candidate regions to feed to the deep neural network classifier. Depending on time of day, we convert our RGB images in order to more accurately extract the appropriate regions of interest and filter them based on color, shape and size.
2017-03-28
Technical Paper
2017-01-0102
Mahdi Heydari, Feng Dang, Ankit Goila, Yang Wang, Hanlong Yang
In this paper, a sensor fusion approach is introduced to estimate lane departure. The proposed algorithm combines the camera, inertial navigation sensor, and GPS data with the vehicle dynamics to estimate the vehicle path and the lane departure time. The lane path and vehicle path are estimated by using Kalman filters. This algorithm can be used to provide early warning for lane departure in order to increase driving safety. By integrating inertial navigation sensor and GPS data, the inertial sensor biases can be estimated and the vehicle path can be estimated where the GPS data is not available or is poor. Additionally, the algorithm can be used to reduce the latency of information embedded in the controls, so that the vehicle lateral control performance can be significantly improved during lane keeping in Advanced Driver Assistance Systems (ADAS) or autonomous vehicles. Furthermore, it improves lane detection reliability in situations when camera fails to detect lanes.
2017-03-28
Technical Paper
2017-01-0109
Yi Zhang, Madeline J. Goh, Vidya Nariyambut Murali
Abstract This work describes a single camera based object distance estimation system. As technology on vehicles is constantly advancing on the road to autonomy, it is critical to know the locations of objects in 3D space for safe behavior of the vehicle. Though significant progress has been made on object detection in 2D sensor space from a single camera, this work additionally estimates the distance to said object without requiring stereo vision or absolute knowledge of vehicle motion. Specifically, our proposed system is comprised of three modules: vision based ego-motion estimation, object-detection, and distance estimation. In particular, we compensate for the vehicle ego-motion by using pin-hole camera model to increase the accuracy of the object distance estimation.
2017-03-28
Technical Paper
2017-01-0099
Jose E. Solomon, Francois Charette
Abstract The proposed technique is a tailored deep neural network (DNN) training approach which uses an iterative process to support the learning of DNNs by targeting their specific misclassification and missed detections. The process begins with a DNN that is trained on freely available annotated image data, which we will refer to as the Base model, where a subset of the categories for the classifier are related to the automotive theater. A small set of video capture files taken from drives with test vehicles are selected, (based on the diversity of scenes, frequency of vehicles, incidental lighting, etc.), and the Base model is used to detect/classify images within the video files. A software application developed specifically for this work then allows for the capture of frames from the video set where the DNN has made misclassifications. The corresponding annotation files for these images are subsequently corrected to eliminate mislabels.
2017-03-28
Technical Paper
2017-01-0395
Xin Xie, Danielle Zeng, Boyang Zhang, Junrui Li, Liping Yan, Lianxiang Yang
Abstract Vehicle front panel is an interior part which has a major impact on the consumers’ experience of the vehicles. To keep a good appearance during long time aging period, most of the front panel is designed as a rough surface. Some types of surface defects on the rough surface can only be observed under the exposure of certain angled sun light. This brings great difficulties in finding surface defects on the production line. This paper introduces a novel polarized laser light based surface quality inspection method for the rough surfaces on the vehicle front panel. By using the novel surface quality inspection system, the surface defects can be detected real-timely even without the exposure under certain angled sun light. The optical fundamentals, theory derivation, experiment setup and testing result are shown in detail in this paper.
2017-03-28
Technical Paper
2017-01-0394
Junrui Li, Ruiyan Yang, Zhen Li, Changqing Du, Dajun Zhou, Lianxiang Yang
Abstract Advanced high-strength steel (AHSS) is gaining popularity in the automotive industry due to its higher final part strength with the better formability compares to the conventional steel. However, the edge fracture occurs during the forming procedure for the pre-strained part. To avoid the edge fracture that happens during the manufacturing, the effect of pre-strain on edge cracking limit needs to be studied. In this paper, digital image correlation (DIC), as an accurate optical method, is adopted for the strain measurement to determining the edge cracking limit. Sets of the wide coupons are pre-strained to obtain the samples at different pre-strain level. The pre-strain of each sample is precisely measured during this procedure using DIC. After pre-straining, the half dog bone samples are cut from these wide coupons. The edge of the notch in the half dog bone samples is created by the punch with 10% clearance for the distinct edge condition.
2017-03-28
Technical Paper
2017-01-1675
Genís Mensa, Núria Parera, Alba Fornells
Abstract Nowadays, the use of high-speed digital cameras to acquire relevant information is a standard for all laboratories and facilities working in passive safety crash testing. The recorded information from the cameras is used to develop and improve the design of vehicles in order to make them safer. Measurements such as velocities, accelerations and distances are computed from high-speed images captured during the tests and represent remarkable data for the post-crash analysis. Therefore, having the exact same position of the cameras is a key factor to be able to compare all the values that are extracted from the images of the tests carried out within a long-term passive safety project. However, since working with several customers involves a large amount of different cars and tests, crash facilities have to readapt for every test mode making it difficult for them to reproduce the correct and precise position of the high-speed cameras throughout the same project.
2017-03-28
Technical Paper
2017-01-1405
Tzu-Sung Wu
Abstract Autonomous Emergency Braking Systems (AEBS) usually contain radar, (stereo) camera and/or LiDAR-based technology to identify potential collision partners ahead of the car, such that to warn the driver or automatically brake to avoid or mitigate a crash. The advantage of camera is less cost: however, is inevitable to face the defects of cameras in AEBS, that is, the image recognition cannot perform good accuracy in the poor or over-exposure light condition. Therefore, the compensation of other sensors is of importance. Motivated by the improvement of false detection, we propose a Pedestrian-and-Vehicle Recognition (PVR) algorithm based on radar to apply to AEBS. The PVR employs the radar cross section (RCS) and standard deviation of width of obstacle to determine whether a threshold value of RCS and standard deviation of width of the pedestrian and vehicle is crossed, and to identity that the objective is a pedestrian or vehicle, respectively.
2017-03-28
Technical Paper
2017-01-1434
Dongran Liu, Marcos Paul Gerardo-Castro, Bruno Costa, Yi Zhang
Abstract Heart rate is one of the most important biological features for health information. Most of the state-of-the-art heart rate monitoring systems rely on contact technologies that require physical contact with the user. In this paper, we discuss a proof-of-concept of a non-contact technology based on a single camera to measure the user’s heart rate in real time. The algorithm estimates the heart rate based on facial color changes. The input is a series of video frames with the automatically detected face of the user. A Gaussian pyramid spatial filter is applied to the inputs to obtain a down-sampled high signal-to-noise ratio images. A temporal Fourier transform is applied to the video to get the signal spectrum. Next, a temporal band-pass filter is applied to the transformed signal in the frequency domain to extract the frequency band of heart beats. We then used the dominant frequency in the Fourier domain to find the heart rate.
Viewing 1 to 30 of 1041

Filter