Channel Pruned YOLOv5-based Deep Learning Approach for Rapid and Accurate Outdoor Obstacles Detection

TL;DR

This paper presents a pruning strategy applied to YOLOv5 for outdoor obstacle detection, significantly reducing model size and inference time while maintaining accuracy, thus enabling rapid and accurate real-time detection.

Contribution

The study introduces a pruning method tailored for YOLOv5, demonstrating substantial model size and speed improvements on an outdoor obstacle dataset with accuracy compensation techniques.

Findings

Model size reduced by 49.7%

Inference time decreased by 52.5%

Accuracy drop mitigated through data processing methods

Abstract

One-stage algorithm have been widely used in target detection systems that need to be trained with massive data. Most of them perform well both in real-time and accuracy. However, due to their convolutional structure, they need more computing power and greater memory consumption. Hence, we applied pruning strategy to target detection networks to reduce the number of parameters and the size of model. To demonstrate the practicality of the pruning method, we select the YOLOv5 model for experiments and provide a data set of outdoor obstacles to show the effect of model. In this specific data set, in the best circumstances, the volume of the network model is reduced by 49.7% compared with the original model, and the reasoning time is reduced by 52.5%. Meanwhile, it also uses data processing methods to compensate for the drop in accuracy caused by pruning.