Pedestrian Detection Algorithm for Intelligent Vehicles in Complex Scenarios
Open Access
Abstract
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.Keywords
Funding Information
- Key Research and Development Project of Jilin Province (20200401112GX)
- Natural Science Foundation of Jilin Province (201501037JC)
This publication has 41 references indexed in Scilit:
- Scale-aware Fast R-CNN for Pedestrian DetectionIEEE Transactions on Multimedia, 2017
- Jointly Learning Deep Features, Deformable Parts, Occlusion and Classification for Pedestrian DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- An Automatic Car Counting System Using OverFeat FrameworkSensors, 2017
- Overview of Environment Perception for Intelligent VehiclesIEEE Transactions on Intelligent Transportation Systems, 2017
- A Machine Learning Approach to Pedestrian Detection for Autonomous Vehicles Using High-Definition 3D Range DataSensors, 2016
- Fast and Efficient Pedestrian Detection via the Cascade Implementation of an Additive Kernel Support Vector MachineIEEE Transactions on Intelligent Transportation Systems, 2016
- Fast multi-feature pedestrian detection algorithm based on histogram of oriented gradient using discrete wavelet transformMultimedia Tools and Applications, 2015
- A Pedestrian-Detection Method Based on Heterogeneous Features and Ensemble of Multi-View–Pose PartsIEEE Transactions on Intelligent Transportation Systems, 2014
- Fast Feature Pyramids for Object DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- In-vehicle technology for self-driving cars: Advantages and challenges for aging driversInternational Journal of Automotive Technology, 2014