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.

Highlights

  • Since the beginning of the 21st century, the growth of the automobile industry has gradually changed people’s daily travel patterns

  • Smart cars obtain the actual road information around the vehicle in real time through the vehicle-mounted camera, and uses the pedestrian detection technology to effectively detect pedestrian objects that appear in front of the vehicle, so that timely feedback and warning can be provided to the driver, and the driver take the correct driving operation to avoid the pedestrians

  • 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

Read more

Summary

Introduction

Since the beginning of the 21st century, the growth of the automobile industry has gradually changed people’s daily travel patterns. Smart cars obtain the actual road information around the vehicle in real time through the vehicle-mounted camera, and uses the pedestrian detection technology to effectively detect pedestrian objects that appear in front of the vehicle, so that timely feedback and warning can be provided to the driver, and the driver take the correct driving operation to avoid the pedestrians This is helpful to ensure the road safety of people and greatly reduce the traffic accident rate [8,9,10,11]. There is no deep learning-based pedestrian detection method that can exhibit accuracy and real-time performance together when applied to complex road scenarios.

Basic Principle of YOLOv3
Limitations of YOLOv3 in Pedestrian Detection
Improved Grid Cell Size
Improved k-Means Clustering Algorithm
Improved Multi-Scale Bounding Box Prediction Based on Receptive Field
Soft-NMS Algorithm
Pedestrian Dataset
Network Training and Evaluation Indicators
Experimental Test Results and Analysis
Object Detection Based on PASCAL VOC 2012 Dataset
Method
Conclusions

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.