scholarly journals Pedestrian Detection under Parallel Feature Fusion Based on Choquet Integral

Symmetry ◽  
2021 ◽  
Vol 13 (2) ◽  
pp. 250
Author(s):  
Rong Yang ◽  
Yun Wang ◽  
Ying Xu ◽  
Li Qiu ◽  
Qiang Li
Keyword(s):  
Feature Fusion ◽  
Choquet Integral ◽  
Detection System ◽  
Pedestrian Detection ◽  
Texture Feature ◽  
Current Method ◽  
Detection Accuracy ◽  
Parallel Feature ◽  
New Feature ◽  
The Cost

Feature-based pedestrian detection method is currently the mainstream direction to solve the problem of pedestrian detection. In this kind of method, whether the appropriate feature can be extracted is the key to the comprehensive performance of the whole pedestrian detection system. It is believed that the appearance of a pedestrian can be better captured by the combination of edge/local shape feature and texture feature. In this field, the current method is to simply concatenate HOG (histogram of oriented gradient) features and LBP (local binary pattern) features extracted from an image to produce a new feature with large dimension. This kind of method achieves better performance at the cost of increasing the number of features. In this paper, Choquet integral based on the signed fuzzy measure is introduced to fuse HOG and LBP descriptors in parallel that is expected to improve accuracy without increasing feature dimensions. The parameters needed in the whole fusion process are optimized by a training algorithm based on genetic algorithm. This architecture has three advantages. Firstly, because the fusion of HOG and LBP features is parallel, the dimensions of the new features are not increased. Secondly, the speed of feature fusion is fast, thus reducing the time of pedestrian detection. Thirdly, the new features after fusion have the advantages of HOG and LBP features, which is helpful to improve the detection accuracy. The series of experimentation with the architecture proposed in this paper reaches promising and satisfactory results.

scholarly journals Multi-Scale Feature Pyramid Network: A Heavily Occluded Pedestrian Detection Network Based on ResNet

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1820
Author(s):  
Xiaotao Shao ◽  
Qing Wang ◽  
Wei Yang ◽  
Yun Chen ◽  
Yi Xie ◽  
...  
Keyword(s):  
Semantic Information ◽  
Detection System ◽  
Pedestrian Detection ◽  
Detection Accuracy ◽  
The Public ◽  
Scale Feature ◽  
Detection Algorithms ◽  
Multi Scale ◽  
Art Works ◽  
Feature Pyramid

The existing pedestrian detection algorithms cannot effectively extract features of heavily occluded targets which results in lower detection accuracy. To solve the heavy occlusion in crowds, we propose a multi-scale feature pyramid network based on ResNet (MFPN) to enhance the features of occluded targets and improve the detection accuracy. MFPN includes two modules, namely double feature pyramid network (FPN) integrated with ResNet (DFR) and repulsion loss of minimum (RLM). We propose the double FPN which improves the architecture to further enhance the semantic information and contours of occluded pedestrians, and provide a new way for feature extraction of occluded targets. The features extracted by our network can be more separated and clearer, especially those heavily occluded pedestrians. Repulsion loss is introduced to improve the loss function which can keep predicted boxes away from the ground truths of the unrelated targets. Experiments carried out on the public CrowdHuman dataset, we obtain 90.96% AP which yields the best performance, 5.16% AP gains compared to the FPN-ResNet50 baseline. Compared with the state-of-the-art works, the performance of the pedestrian detection system has been boosted with our method.

scholarly journals Anchor Generation Optimization and Region of Interest Assignment for Vehicle Detection

Sensors ◽  
2019 ◽  
Vol 19 (5) ◽  
pp. 1089 ◽  
Author(s):  
Ye Wang ◽  
Zhenyi Liu ◽  
Weiwen Deng
Keyword(s):  
Pedestrian Detection ◽  
Region Of Interest ◽  
Vehicle Detection ◽  
Detection Accuracy ◽  
Fixed Size ◽  
Feature Maps ◽  
Feature Map ◽  
Bounding Box ◽  
New Feature ◽  
And Training

Region proposal network (RPN) based object detection, such as Faster Regions with CNN (Faster R-CNN), has gained considerable attention due to its high accuracy and fast speed. However, it has room for improvements when used in special application situations, such as the on-board vehicle detection. Original RPN locates multiscale anchors uniformly on each pixel of the last feature map and classifies whether an anchor is part of the foreground or background with one pixel in the last feature map. The receptive field of each pixel in the last feature map is fixed in the original faster R-CNN and does not coincide with the anchor size. Hence, only a certain part can be seen for large vehicles and too much useless information is contained in the feature for small vehicles. This reduces detection accuracy. Furthermore, the perspective projection results in the vehicle bounding box size becoming related to the bounding box position, thereby reducing the effectiveness and accuracy of the uniform anchor generation method. This reduces both detection accuracy and computing speed. After the region proposal stage, many regions of interest (ROI) are generated. The ROI pooling layer projects an ROI to the last feature map and forms a new feature map with a fixed size for final classification and box regression. The number of feature map pixels in the projected region can also influence the detection performance but this is not accurately controlled in former works. In this paper, the original faster R-CNN is optimized, especially for the on-board vehicle detection. This paper tries to solve these above-mentioned problems. The proposed method is tested on the KITTI dataset and the result shows a significant improvement without too many tricky parameter adjustments and training skills. The proposed method can also be used on other objects with obvious foreshortening effects, such as on-board pedestrian detection. The basic idea of the proposed method does not rely on concrete implementation and thus, most deep learning based object detectors with multiscale feature maps can be optimized with it.

Research and Manufacture on the Detection System on the Rifle Curve, Straightness and Roughness of the Firearm Bore Wall

2012 ◽  
Vol 229-231 ◽  
pp. 1361-1364
Author(s):  
Pen Ren Chen ◽  
Kai Mao ◽  
Yu Mei Sun
Keyword(s):  
Crucial Role ◽  
Detection System ◽  
Technical Problem ◽  
Current Method ◽  
System Structure ◽  
Detection Accuracy ◽  
Current Standard ◽  
Computer Image Processing ◽  
Quality Of Products

The rifle curve, straightness and roughness of the firearm bore wall play a crucial role to the shooting accuracy and distance. Detection on the bore wall is therefore very important on purpose of improving the accuracy of fine processing and ensuring the quality of products. However, the regular detection method is helpless due to the space and size restriction of the bore wall. In order to solve this technical problem, a detection system for the bore wall is discussed, the system structure is briefly introduced, the system principle is analyzed and the application value of popularization is also pointed out in this paper. The detection accuracy has exceeded the current standard at home and abroad and reached the level of nm. The rifle curve, straightness and roughness of the firearm bore wall play a crucial role to the shooting accuracy and distance. Detection on the bore wall is therefore very important on purpose of improving the accuracy of fine processing and ensuring the quality of product. As for the detection of rifle curve, straightness and roughness of the firearm bore wall, the current method is only limit to the endoscopic camera and computer image processing, and the effect on the larger flaw is obvious but can not reach the fine requirement for the detection of the new products.

scholarly journals Improved Pedestrian Detection Based on Extended Histogram of Oriented Gradients

2013 ◽  
Vol 347-350 ◽  
pp. 3815-3820
Author(s):  
Li Hong Zhang ◽  
Lin Li
Keyword(s):  
Detection System ◽  
Pedestrian Detection ◽  
Human Detection ◽  
Support Vector ◽  
Detection Accuracy ◽  
Histogram Of Oriented Gradients ◽  
Multi Scale ◽  
Suppression Method ◽  
Overlap Ratio ◽  
Scale Detection

In order to further improve pedestrian detection accuracy and avoid the disadvantage of original histogram of oriented gradients (HOG), differential template, overlap ratio and normalization method and so on are improved when HOG features are extracted, then more gradient information are extracted and feature description operators can be obtained which describe human detail features better in lager image regions or detection windows. Considering speed, we select support vector machine (SVM) using linear function kernel as a classifier. Multi-scale detection technique and non maxima suppression method are employed for precisely locating the pedestrians in the image. Experiments show that the human detection system improves detection accuracy and still maintains a relatively satisfactory speed.

Research of Infrared Video Fatigue Detection Based on SoPC

2013 ◽  
Vol 411-414 ◽  
pp. 1488-1494 ◽  
Author(s):  
Xian Jun Wang ◽  
Xiang Hui Yuan
Keyword(s):  
Parallel Processing ◽  
High Speed ◽  
Feature Fusion ◽  
Detection System ◽  
Detection Accuracy ◽  
Driver Fatigue ◽  
Difference Of Gaussian ◽  
Infrared Video ◽  
Boosting Algorithm ◽  
Fatigue Detection

A new high-speed infrared video-based fatigue detection system was developed using a system on a programmable chip (SoPC) in this study. Based on the limitations of PERCLOS, we merged the eyes and mouth fatigue related characteristics to improve detection accuracy, used a Difference of Gaussian (DoG) filter and Ada-boosting algorithm to implement driver fatigue detection based on multi-feature fusion. The detection system was produced using FPGA with a parallel processing structure and pipeline technology. This system is innovative and it can detect fatigued states efficiently and rapidly.

Study on the Method of Pedestrian Detection in Automobile Safety System

2012 ◽  
Vol 580 ◽  
pp. 118-121
Author(s):  
Zhong Hao Bai ◽  
Zhi Peng Ding ◽  
Qiang Yan
Keyword(s):  
Traffic Accidents ◽  
Detection Method ◽  
Detection System ◽  
Pedestrian Detection ◽  
Active Safety ◽  
Detection Accuracy ◽  
Cascade Algorithm ◽  
Automobile Safety ◽  
High Detection ◽  
Detection Effect

In order to improve automobile active safety performance, and reduce the traffic accidents between pedestrians and vehicles, a pedestrian detection method combined with pedestrian contour features is proposed based on the combination of the reliable Adaboost and SVM. For the requirements of fast and accurate pedestrian detection system, ten types of haar-like features are given as the coarse features firstly, and which are trained through Adaboost cascade algorithm to ensure the system with a high detection speed. Then, the hog features of strong ability to distinguish pedestrians are selected as the fine features, and the pedestrian classifier is got by using SVM of different kernels to improve the detection accuracy. It is shown that the method has a higher detection rate and achieves a better detection effect.

Vehicle and Pedestrian Detection Based on Multi-level Feature Fusion in Autonomous Driving

2020 ◽  
Vol 13 ◽  
Author(s):  
Chen Guoqiang ◽  
Yi Huailong ◽  
Mao Zhuangzhuang
Keyword(s):  
Autonomous Vehicles ◽  
Feature Fusion ◽  
Pedestrian Detection ◽  
Autonomous Driving ◽  
Seasonal Effects ◽  
Detection Accuracy ◽  
Semantic Features ◽  
Feature Maps ◽  
Safe Driving ◽  
Multi Level

Aims: The factors including light, weather, dynamic objects, seasonal effects and structures bring great challenges for the autonomous driving algorithm in the real world. Autonomous vehicles can detect different object obstacles in complex scenes to ensure safe driving. Background: The ability to detect vehicles and pedestrians is critical to the safe driving of autonomous vehicles. Automated vehicle vision systems must handle extremely wide and challenging scenarios. Objective: The goal of the work is to design a robust detector to detect vehicles and pedestrians. The main contribution is that the Multi-level Feature Fusion Block (MFFB) and the Detector Cascade Block (DCB) are designed. The multi-level feature fusion and multi-step prediction are used which greatly improve the detection object precision. Methods: The paper proposes a vehicle and pedestrian object detector, which is an end-to-end deep convolutional neural network. The key parts of the paper are to design the Multi-level Feature Fusion Block (MFFB) and Detector Cascade Block (DCB). The former combines inherent multi-level features by combining contextual information with useful multi-level features that combine high resolution but low semantics and low resolution but high semantic features. The latter uses multi-step prediction, cascades a series of detectors, and combines predictions of multiple feature maps to handle objects of different sizes. Results: The experiments on the RobotCar dataset and the KITTI dataset show that our algorithm can achieve high precision results through real-time detection. The algorithm achieves 84.61% mAP on the RobotCar dataset and is evaluated on the well-known KITTI benchmark dataset, achieving 81.54% mAP. In particular, the detection accuracy of a single-category vehicle reaches 90.02%. Conclusion: The experimental results show that the proposed algorithm has a good trade-off between detection accuracy and detection speed, which is beyond the current state-of-the-art RefineDet algorithm. The 2D object detector is proposed in the paper, which can solve the problem of vehicle and pedestrian detection and improve the accuracy, robustness and generalization ability in autonomous driving.

scholarly journals A Vehicle and Pedestrian Detection Method Based on Improved YOLOv4-Tiny

2022 ◽  
Vol 11 (01) ◽  
pp. 22-26
Author(s):  
Hui Xiang ◽  
Junyan Han ◽  
Hanqing Wang ◽  
Hao Li ◽  
Shangqing Li ◽  
...  
Keyword(s):  
Detection Method ◽  
Feature Fusion ◽  
Pedestrian Detection ◽  
Mean Average Precision ◽  
Detection Methods ◽  
Small Scale ◽  
Detection Accuracy ◽  
Improved Method ◽  
Average Precision ◽  
The Mean

Aiming at the problems of low detection accuracy and poor recognition effect of small-scale targets in traditional vehicle and pedestrian detection methods, a vehicle and pedestrian detection method based on improved YOLOv4-Tiny is proposed. On the basis of YOLOv4-Tiny, the 8-fold down sampling feature layer was added for feature fusion, the PANet structure was used to perform bidirectional fusion for the deep and shallow features from the output feature layer of backbone network, and the detection head for small targets was added. The results show that the mean average precision of the improved method has reached 85.93%, and the detection performance is similar to that of YOLOv4. Compared with the YOLOv4-Tiny, the mean average precision of the improved method is increased by 24.45%, and the detection speed reaches 67.83FPS, which means that the detection effect is significantly improved and can meet the real-time requirements.

Sign in / Sign up

Export Citation Format

Share Document