Accurate object detection on the road is the most important requirement of autonomous vehicles. Extensive work has been accomplished for car, pedestrian, and cyclist detection; however, comparatively, very few efforts have been put into 2D object detection. In this article, a dynamic approach is investigated to design a perfect unified neural network that could achieve the best results based on our available hardware. The proposed architecture is based on CSPNet for feature extraction in an end-to-end way. The net extracts visual features by using backbone subnet, visual object detection is based on a feature pyramid network (FPN). In order to increase the net flexibility, an auto-anchor generating method is applied to the detection layer that makes the net suitable for any datasets. For fine-tuning the net, activation, optimization, and loss functions are considered along with multiple check points. The proposed net is trained and tested based on the benchmark KITTI dataset. Our extensive experiments show that the proposed model for visual object detection is superior to others, where other nets output very low accuracy for pedestrian and cyclist detection, our proposed model achieves 99.3% recall rate based on our dataset.
Autonomous vehicle has come a long way to reach on the road; however accurate road perception in real-time is one of the crucial factors towards its success. The biggest challenge in this direction includes occlusion, truncation, lighting conditions, and complex backgrounds. In order to improve the accuracy and detection speed for vehicle detection, a dynamic scaling network is proposed that assists in constructing a balanced shape neural network to achieve optimum accuracy with minimal hardware. The network architecture is influenced by YOLOv5 and is composed of Cross-Stage Partial Network (CSPNet) as its backbone. In order to go even further, we have proposed an auto-anchor generating method that makes the network suitable for any datasets. Our neural network is fine-tuned by using activation, loss, and optimization functions so as to get the optimum results. Our experimental results demonstrate that the proposed net provides comparable performance of YOLOv4 and Faster R-CNN based on KITTI dataset as the benchmark.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.