scholarly journals An FPGA-Based Ultra-High-Speed Object Detection Algorithm with Multi-Frame Information Fusion

Sensors ◽  
2019 ◽  
Vol 19 (17) ◽  
pp. 3707 ◽  
Author(s):  
Xianlei Long ◽  
Shenhua Hu ◽  
Yiming Hu ◽  
Qingyi Gu ◽  
Idaku Ishii
Keyword(s):  
Object Detection ◽  
Information Fusion ◽  
High Speed ◽  
Clock Cycle ◽  
Image Data ◽  
Detection Algorithm ◽  
Support Vector ◽  
Fusion Model ◽  
Ultra High Speed ◽  
Field Programmable

An ultra-high-speed algorithm based on Histogram of Oriented Gradient (HOG) and Support Vector Machine (SVM) for hardware implementation at 10,000 frames per second (FPS) under complex backgrounds is proposed for object detection. The algorithm is implemented on the field-programmable gate array (FPGA) in the high-speed-vision platform, in which 64 pixels are input per clock cycle. The high pixel parallelism of the vision platform limits its performance, as it is difficult to reduce the strides between detection windows below 16 pixels, thus introduce non-negligible deviation of object detection. In addition, limited by the transmission bandwidth, only one frame in every four frames can be transmitted to PC for post-processing, that is, 75% image information is wasted. To overcome the mentioned problem, a multi-frame information fusion model is proposed in this paper. Image data and synchronization signals are first regenerated according to image frame numbers. The maximum HOG feature value and corresponding coordinates of each frame are stored in the bottom of the image with that of adjacent frames’. The compensated ones will be obtained through information fusion with the confidence of continuous frames. Several experiments are conducted to demonstrate the performance of the proposed algorithm. As the evaluation result shows, the deviation is reduced with our proposed method compared with the existing one.

A novel hardware-oriented ultra-high-speed object detection algorithm based on convolutional neural network

2019 ◽  
Vol 17 (5) ◽  
pp. 1703-1714 ◽  
Author(s):  
Jianquan Li ◽  
Xianlei Long ◽  
Shenhua Hu ◽  
Yiming Hu ◽  
Qingyi Gu ◽  
...  
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
High Speed ◽  
Detection Algorithm ◽  
Ultra High Speed

scholarly journals Recognition of Human Emotion Detection and Annotation, using Local Descriptor and Support Vector Machine

2019 ◽  
Vol 9 (2) ◽  
pp. 2838-2843
Keyword(s):  
Support Vector Machine ◽  
Object Detection ◽  
Dynamic Environment ◽  
Detection Algorithm ◽  
Research Area ◽  
Multimedia Data ◽  
Video Annotation ◽  
Support Vector ◽  
People Detection ◽  
Local Descriptor

In multimedia data analysis, video tagging is the most challenging and active research area. In which finding or detecting the object with the dynamic environment is most challenging. Object detection and its validation are an essential functional step in video annotation. Considering the above challenges, the proposed system designed to presents the people detection module from a complex background. Detected persons are validated for further annotation process. Using publically available dataset for module design, Viola-Jones object detection algorithm is used for person detection. Support Vector Machine (SVM) authenticate the detected object/person based on it local features using Local Binary Pattern (LBP). The performance of the proposed system presents given architecture is effectively annotating the detected people emotion.

A Hardware-Oriented Algorithm for Ultra-High-Speed Object Detection

2019 ◽  
Vol 19 (10) ◽  
pp. 3818-3831 ◽  
Author(s):  
Jianquan Li ◽  
Xilong Liu ◽  
Fangfang Liu ◽  
De Xu ◽  
Qingyi Gu ◽  
...  
Keyword(s):  
Object Detection ◽  
High Speed ◽  
Ultra High Speed

scholarly journals A Deep Learning-Based Fragment Detection Approach for the Arena Fragmentation Test

2020 ◽  
Vol 10 (14) ◽  
pp. 4744
Author(s):  
Hyukzae Lee ◽  
Jonghee Kim ◽  
Chanho Jung ◽  
Yongchan Park ◽  
Woong Park ◽  
...  
Keyword(s):  
Image Processing ◽  
Deep Learning ◽  
Object Detection ◽  
High Speed ◽  
Detection Algorithm ◽  
Learning Technologies ◽  
Experimental Conditions ◽  
Fragmentation Test ◽  
Detection Approach ◽  
Previous Image

The arena fragmentation test (AFT) is one of the tests used to design an effective warhead. Conventionally, complex and expensive measuring equipment is used for testing a warhead and measuring important factors such as the size, velocity, and the spatial distribution of fragments where the fragments penetrate steel target plates. In this paper, instead of using specific sensors and equipment, we proposed the use of a deep learning-based object detection algorithm to detect fragments in the AFT. To this end, we acquired many high-speed videos and built an AFT image dataset with bounding boxes of warhead fragments. Our method fine-tuned an existing object detection network named the Faster R-convolutional neural network (CNN) on this dataset with modification of the network’s anchor boxes. We also employed a novel temporal filtering method, which was demonstrated as an effective non-fragment filtering scheme in our recent previous image processing-based fragment detection approach, to capture only the first penetrating fragments from all detected fragments. We showed that the performance of the proposed method was comparable to that of a sensor-based system under the same experimental conditions. We also demonstrated that the use of deep learning technologies in the task of AFT significantly enhanced the performance via a quantitative comparison between our proposed method and our recent previous image processing-based method. In other words, our proposed method outperformed the previous image processing-based method. The proposed method produced outstanding results in terms of finding the exact fragment positions.

Arc Detection and Recognition in the Pantograph-Catenary System Based on Multi-Information Fusion

2020 ◽  
Vol 2674 (10) ◽  
pp. 229-240
Author(s):  
Shize Huang ◽  
Wei Chen ◽  
Bo Sun ◽  
Ting Tao ◽  
Lingyu Yang
Keyword(s):  
Visible Light ◽  
Information Fusion ◽  
High Speed ◽  
Evidence Theory ◽  
Detection Methods ◽  
Fusion Method ◽  
Fusion Model ◽  
Threshold Method ◽  
High Speed Trains ◽  
Catenary System

The pantograph-catenary system is critical to high-speed railways. Electric arcs in the pantograph-catenary system indicate possible damages to the whole railway system, and detecting them in time has been a critical task. In this paper, a fusion method for the pantograph-catenary arc detection based on multi-type videos is proposed. First, convolutional neural network (CNN) is employed to detect arcs in visible light images, and a threshold method is applied to identify arcs in infrared images. Second, the CNN-based environment perception model is established on visible light images. It obtains the dynamical adjustment of the reliability weights for different scenarios where trains usually work. Finally, the information fusion model based on evidence theory uses those weights and integrates the detection results on visible light images and infrared results. The experimental results demonstrate the fusion method can avoid misjudgments of the two individual detection methods in certain scenarios, and perform better than each of them. This approach can adapt to the complex environments of high-speed trains.

scholarly journals Support Vector Machine working on FPGA and the segmentation method of brain MR screening

2017 ◽  
Vol 4 (3) ◽  
pp. 120 ◽  
Author(s):  
Fatih Şişik ◽  
Eser Sert
Keyword(s):  
Integrated Circuit ◽  
Field Programmable Gate Array ◽  
High Speed ◽  
Hardware Description Language ◽  
Support Vector ◽  
Segmentation Method ◽  
Description Language ◽  
Field Programmable ◽  
Hardware Description ◽  
Very High

Alan Programlanabilir Kapı Dizileri (Field Programmable Gate Array-FPGA) programlanabilir sayısal bloklar ve bağlantılarını içeren cihazlar olup çok esnek ve hızlı çalışabilme özelliklerine sahiptir. Programlanabilen bu sayısal kapılar sayesinde karmaşık tasarımlar kolay bir şekilde geliştirilebilmektedir. FPGA’lar küçük boyutlarda olup bilgisayardan bağımsız mobil olarak ve bilgisayarlardan daha yüksek hızlarda çalışabilmektedirler. Veri madenciliğinin görevlerinden biri olan sınıflandırma probleminin çözümü için geliştirilmiş önemli makine öğrenimi algoritmalarından biri Destek Vektör Makineleri’ dir. Literatürde Destek Vektör Makineleri’ nin diğer birçok tekniğe göre daha başarılı sonuçlar verdiği kanıtlanmıştır. Tümör analizi, yüz tanıma, robotik göz oluşturma gibi konular, araştırmacıların görüntü işleme alanında yoğun olarak üzerinde çalıştıkları güncel, önemli ve zor problemlerden bazılarıdır. Bilgisayarda yapılan tümör analizinde, grafik ve resimlerin işlenmesinde yavaş işlem yapma ve aynı zamanda mobil olmama sorunlarından, FPGA donanımı ile görüntü işlemede bu sorunların üstesinden gelinmektedir. Bu çalışmada FPGA donanımında çalışan destek vektör makinası kullanılarak daha gerçekçi tümör analizi yapılarak tümörlü bölgelerin bulunması ve gerekli analiz sonuçlarının gösterilmesi amaçlanmaktadır. Böylece sağlık alanında da kullanılabilecek yararlı bir donanımın tasarımı gerçekleştirilecektir. Dolayısıyla gömülü sistemlerle anlatılan bu işlem süreçlerini gerçekleştiren çalışma sayısı çok az olduğundan çalışma özgün değer taşımaktadır. Buna ek olarak, FPGA’ ya özgü donanım tanımlama dillerinden biri olan Çok Yüksek Hızlı Tümleşik Devre Tanımlama Dili (Very High Speed Integrated Circuit  Hardware Description Language- VHDL) kullanılacaktır. Bölütleme sonucunun değerlendirilmesi için Uniformity Measure (UM) kullanılmıştır. UM değerlendirme sonucunun başarılı olduğu görülmüştür. Anahtar Kelimeler: Alan Programlanabilir Kapı Dizileri, FPGA, çok yüksek hızlı tümleşik devre tanımlama dili, vhdl, segmentasyon, destek vektör makinesi

scholarly journals Reconfigurable Hardware Design for Automatic Epilepsy Seizure Detection using EEG Signals

2020 ◽  
Vol 10 (3) ◽  
pp. 5803-5807
Author(s):  
S. S. Rafiammal ◽  
D. N. Jamal ◽  
S. K. Mohideen
Keyword(s):  
Learning Algorithm ◽  
Seizure Detection ◽  
Detection Algorithm ◽  
Experimental Results ◽  
Support Vector ◽  
Detection Accuracy ◽  
Severe Injuries ◽  
Hardware Implementations ◽  
Field Programmable ◽  
Health Related

Reconfigurable circuit designs for automatic seizure detection devices are essential to prevent epilepsy affected people from severe injuries and other health-related problems. In this proposed design, an automatic seizure detection algorithm based on the Linear binary Support Vector Machine learning algorithm (LSVM) is developed and implemented in a Field-Programmable Gate Array (FPGA). The experimental results showed that the mean detection accuracy is 86% and sensitivity is 97%. The resource utilization of the implemented design is less when compared to existing hardware implementations. The power consumption of the proposed design is 76mW at 100MHz. The experimental results assure that a physician can make use of this proposed design in detecting seizure events.

scholarly journals Enhancing Railway Maintenance Safety Using Open-Source Computer Vision

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Donghee Shin ◽  
Jangwon Jin ◽  
Jooyoung Kim
Keyword(s):  
Computer Vision ◽  
Social Issue ◽  
Monitoring System ◽  
High Speed ◽  
Image Data ◽  
Detection Algorithm ◽  
Prevention System ◽  
Maintenance Work ◽  
Tunnel Monitoring ◽  
Railway Maintenance

As high-speed railways continue to be constructed, more maintenance work is needed to ensure smooth operation. However, this leads to frequent accidents involving maintenance workers at the tracks. Although the number of such accidents is decreasing, there is an increase in the number of casualties. When a maintenance worker is hit by a train, it invariably results in a fatality; this is a serious social issue. To address this problem, this study utilized the tunnel monitoring system installed on trains to prevent railway accidents. This was achieved by using a system that uses image data from the tunnel monitoring system to recognize railway signs and railway tracks and detect maintenance workers on the tracks. Images of railway signs, tracks, and maintenance workers on the tracks were recorded through image data. The Computer Vision OpenCV library was utilized to extract the image data. A recognition and detection algorithm for railway signs, tracks, and maintenance workers was constructed to improve the accuracy of the developed prevention system.

scholarly journals Convolutional Neural Networks-Based Object Detection Algorithm by Jointing Semantic Segmentation for Images

Sensors ◽  
2020 ◽  
Vol 20 (18) ◽  
pp. 5080
Author(s):  
Baohua Qiang ◽  
Ruidong Chen ◽  
Mingliang Zhou ◽  
Yuanchao Pang ◽  
Yijie Zhai ◽  
...  
Keyword(s):  
Object Detection ◽  
Real Time ◽  
Image Data ◽  
Semantic Segmentation ◽  
Image Understanding ◽  
Detection Algorithm ◽  
Vital Role ◽  
Multi Scale ◽  
Segmentation Task ◽  
High Level

In recent years, increasing image data comes from various sensors, and object detection plays a vital role in image understanding. For object detection in complex scenes, more detailed information in the image should be obtained to improve the accuracy of detection task. In this paper, we propose an object detection algorithm by jointing semantic segmentation (SSOD) for images. First, we construct a feature extraction network that integrates the hourglass structure network with the attention mechanism layer to extract and fuse multi-scale features to generate high-level features with rich semantic information. Second, the semantic segmentation task is used as an auxiliary task to allow the algorithm to perform multi-task learning. Finally, multi-scale features are used to predict the location and category of the object. The experimental results show that our algorithm substantially enhances object detection performance and consistently outperforms other three comparison algorithms, and the detection speed can reach real-time, which can be used for real-time detection.

A Moving Object Detection Algorithm Based on ORB under Dynamic Scene

2014 ◽  
Vol 602-605 ◽  
pp. 1638-1641 ◽  
Author(s):  
Wen Hao Luo
Keyword(s):  
Object Detection ◽  
Difference Method ◽  
High Speed ◽  
Detection Algorithm ◽  
Moving Object Detection ◽  
Moving Object ◽  
Transformation Model ◽  
Dynamic Scene ◽  
Frame Difference ◽  
Inter Frame

In this thesis, a moving object detection algorithm under dynamic scene is proposed, which is based on ORB feature. Firstly, we extract feature points and match them by using ORB. We then obtain global motion compensation image by parameters of transformation matrix based on the RANSAC method. Finally, we use the inter-frame difference method to achieve the detection of moving targets. The high speed and accuracy of ORB feature point matching method, as well as the effectiveness of the RANSAC method for removing outliers ensure accurate calculation of parameters of affine transformation model. Combined with inter-frame difference method, foreground objects can be detected entirely. Experiment results show that the algorithm can accurately detect moving objects, and to some extent, it can solve the issue of real-time detection.

Sign in / Sign up

Export Citation Format

Share Document