Real-time DSP implementation of Pedestrian Detection algorithm using HOG features

Due to the limitation of energy consumption and power consumption, the embedded platform cannot meet the real-time requirements of the far-infrared image pedestrian detection algorithm. To solve this problem, this paper proposes a new real-time infrared pedestrian detection algorithm (RepVGG-YOLOv4, Rep-YOLO), which uses RepVGG to reconstruct the YOLOv4 backbone network, reduces the amount of model parameters and calculations, and improves the speed of target detection; using space spatial pyramid pooling (SPP) obtains different receptive field information to improve the accuracy of model detection; using the channel pruning compression method reduces redundant parameters, model size, and computational complexity. The experimental results show that compared with the YOLOv4 target detection algorithm, the Rep-YOLO algorithm reduces the model volume by 90%, the floating-point calculation is reduced by 93.4%, the reasoning speed is increased by 4 times, and the model detection accuracy after compression reaches 93.25%.

Download Full-text

AN OPTIONAL THRESHOLD WITH SVM CLOUD DETECTION ALGORITHM AND DSP IMPLEMENTATION

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprsarchives-xli-b8-771-2016 ◽

2016 ◽

Vol XLI-B8 ◽

pp. 771-777 ◽

Cited By ~ 3

Author(s):

Guoqing Zhou ◽

Xiang Zhou ◽

Tao Yue ◽

Yilong Liu

Keyword(s):

Real Time ◽

Detection Algorithm ◽

High Accuracy ◽

Svm Classifier ◽

Detection Accuracy ◽

Landsat 8 ◽

Cloud Detection ◽

Threshold Method ◽

Dsp Implementation ◽

Svm Algorithm

This paper presents a method which combines the traditional threshold method and SVM method, to detect the cloud of Landsat-8 images. The proposed method is implemented using DSP for real-time cloud detection. The DSP platform connects with emulator and personal computer. The threshold method is firstly utilized to obtain a coarse cloud detection result, and then the SVM classifier is used to obtain high accuracy of cloud detection. More than 200 cloudy images from Lansat-8 were experimented to test the proposed method. Comparing the proposed method with SVM method, it is demonstrated that the cloud detection accuracy of each image using the proposed algorithm is higher than those of SVM algorithm. The results of the experiment demonstrate that the implementation of the proposed method on DSP can effectively realize the real-time cloud detection accurately.

Download Full-text

Real-time Pedestrian Detection Algorithm Based on Improved YOLOv3

Journal of Physics Conference Series ◽

10.1088/1742-6596/2002/1/012075 ◽

2021 ◽

Vol 2002 (1) ◽

pp. 012075

Author(s):

Xianchang Xi ◽

Zhikai Huang ◽

Lingyi Ning ◽

Yang Zhang

Keyword(s):

Real Time ◽

Pedestrian Detection ◽

Detection Algorithm

Download Full-text

AN OPTIONAL THRESHOLD WITH SVM CLOUD DETECTION ALGORITHM AND DSP IMPLEMENTATION

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xli-b8-771-2016 ◽

2016 ◽

Vol XLI-B8 ◽

pp. 771-777

Author(s):

Guoqing Zhou ◽

Xiang Zhou ◽

Tao Yue ◽

Yilong Liu

Keyword(s):

Real Time ◽

Detection Algorithm ◽

High Accuracy ◽

Svm Classifier ◽

Detection Accuracy ◽

Landsat 8 ◽

Cloud Detection ◽

Threshold Method ◽

Dsp Implementation ◽

Svm Algorithm

This paper presents a method which combines the traditional threshold method and SVM method, to detect the cloud of Landsat-8 images. The proposed method is implemented using DSP for real-time cloud detection. The DSP platform connects with emulator and personal computer. The threshold method is firstly utilized to obtain a coarse cloud detection result, and then the SVM classifier is used to obtain high accuracy of cloud detection. More than 200 cloudy images from Lansat-8 were experimented to test the proposed method. Comparing the proposed method with SVM method, it is demonstrated that the cloud detection accuracy of each image using the proposed algorithm is higher than those of SVM algorithm. The results of the experiment demonstrate that the implementation of the proposed method on DSP can effectively realize the real-time cloud detection accurately.

Download Full-text

A REAL-TIME DETECTION ALGORITHM FOR VISION-BASED PEDESTRIAN PROTECTION

International Journal of Information Acquisition ◽

10.1142/s0219878908001466 ◽

2008 ◽

Vol 05 (01) ◽

pp. 11-30 ◽

Cited By ~ 1

Author(s):

GUANGLIN MA ◽

SU-BIRM PARK ◽

ALEXANDER IOFFE ◽

STEFAN MÜLLER-SCHNEIDERS ◽

ANTON KUMMERT

Keyword(s):

Real Time ◽

Pedestrian Detection ◽

Ground Plane ◽

Detection Algorithm ◽

Obstacle Detection ◽

Low Contrast ◽

The Road ◽

Novel Approach ◽

Real Time Detection ◽

Flat Ground

This paper discusses the robust, real-time detection of stationary and moving pedestrians utilizing a single car-mounted monochrome camera. First, the system detects potential pedestrians above the ground plane by combining conventional Inverse Perspective Mapping (IPM)-based obstacle detection with the vertical 1D profile evaluation of the IPM detection result. Usage of the vertical profile increases the robustness of detection in low-contrast images as well as the detection of distant pedestrians significantly. A fast digital image stabilization algorithm is used to compensate for erroneous detections whenever the flat ground plane assumption is an inaccurate model of the road surface. Finally, a low-level pedestrian-oriented segmentation and fast symmetry search on the leg region of pedestrians is also presented. A novel approach termed Pedestrian Detection Strip (PDS) is used to improve the calculation time by a factor of six compared to conventional approaches.

Download Full-text

Research and Implementation of Real-Time Pedestrian Detection Algorithm

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.945-949.1837 ◽

2014 ◽

Vol 945-949 ◽

pp. 1837-1841

Author(s):

Mei Hua Xu ◽

Huai Meng Zheng ◽

Chen Jun Xia

Keyword(s):

Real Time ◽

Pedestrian Detection ◽

Local Binary Patterns ◽

Detection Algorithm ◽

Typical Feature ◽

Detection Methods ◽

Driving System ◽

The Real ◽

Time Performance ◽

Speed Up

Pedestrian detection has a broad application prospect in automotive assisting driving system, but the real time performance is very poor in most common used detection methods. This paper presents a fast algorithm to realize the real-time pedestrian detection. The Local Binary Patterns (LBP) is used to describe the local texture information with the feature of less calculation, the HOG classifier to extract a typical feature of pedestrian’s edge, and then SVM to train and classify on the databases of INRIA and MIT. While scanning the images, interest regions are extracted to speed up the detection. Series of experiment results shows that the proposed pedestrian detecting strategy is effective and efficient.

Download Full-text

A pedestrian detection algorithm for low light and dense crowd Based on improved YOLO algorithm

MATEC Web of Conferences ◽

10.1051/matecconf/202235503020 ◽

2022 ◽

Vol 355 ◽

pp. 03020

Author(s):

Yitong Mao

Keyword(s):

Real Time ◽

Pedestrian Detection ◽

Detection Algorithm ◽

Low Light ◽

Convolutional Network ◽

Detection Model ◽

Aerial View ◽

Weak Light ◽

Ap Index ◽

Dense Crowd

The real-time pedestrian detection algorithm requires the model to be lightweight and robust. At the same time, the pedestrian object detection problem has the characteristics of aerial view Angle shooting, object overlap and weak light, etc. In order to design a more robust real-time detection model in weak light and crowded scene, this paper based on YOLO, raised a more efficient convolutional network. The experimental results show that, compared with YOLOX Network, the improved YOLO Network has a better detection effect in the lack of light scene and dense crowd scene, has a 5.0% advantage over YOLOX-s for pedestrians AP index, and has a 44.2% advantage over YOLOX-s for fps index.

Download Full-text

Pedestrian Detection Algorithm for Intelligent Vehicles in Complex Scenarios

Sensors ◽

10.3390/s20133646 ◽

2020 ◽

Vol 20 (13) ◽

pp. 3646

Author(s):

Jingwei Cao ◽

Chuanxue Song ◽

Silun Peng ◽

Shixin Song ◽

Xu Zhang ◽

...

Keyword(s):

Real Time ◽

Traffic Accidents ◽

Clustering Algorithm ◽

Pedestrian Detection ◽

Grid Cell ◽

Detection Algorithm ◽

Intelligent Vehicles ◽

Detection Accuracy ◽

Detection Algorithms ◽

Driving Assistance

Pedestrian detection is an important aspect of the development of intelligent vehicles. To address problems in which traditional pedestrian detection is susceptible to environmental factors and are unable to meet the requirements of accuracy in real time, this study proposes a pedestrian detection algorithm for intelligent vehicles in complex scenarios. YOLOv3 is one of the deep learning-based object detection algorithms with good performance at present. In this article, the basic principle of YOLOv3 is elaborated and analyzed firstly to determine its limitations in pedestrian detection. Then, on the basis of the original YOLOv3 network model, many improvements are made, including modifying grid cell size, adopting improved k-means clustering algorithm, improving multi-scale bounding box prediction based on receptive field, and using Soft-NMS algorithm. Finally, based on INRIA person and PASCAL VOC 2012 datasets, pedestrian detection experiments are conducted to test the performance of the algorithm in various complex scenarios. The experimental results show that the mean Average Precision (mAP) value reaches 90.42%, and the average processing time of each frame is 9.6 ms. Compared with other detection algorithms, the proposed algorithm exhibits accuracy and real-time performance together, good robustness and anti-interference ability in complex scenarios, strong generalization ability, high network stability, and detection accuracy and detection speed have been markedly improved. Such improvements are significant in protecting the road safety of pedestrians and reducing traffic accidents, and are conducive to ensuring the steady development of the technological level of intelligent vehicle driving assistance.

Download Full-text