Paper
11 October 2023 Optimization and implementation of vehicle detection algorithm for tiny objects
Jing Shi
Author Affiliations +
Proceedings Volume 12800, Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023); 128000Q (2023) https://doi.org/10.1117/12.3004036
Event: 6th International Conference on Computer Information Science and Application Technology (CISAT 2023), 2023, Hangzhou, China
Abstract
To address the issue of current target detection models struggling to detect small vehicles and complex depth models being ill-suited for embedded platforms with limited computing power and memory, NWD and IoU are combined for tiny object detection, and the lightweight backbone network EfficientFormer is used to replace the YOLOv5 model backbone, which finally improves the tiny object detection effect while reducing the model parameters to achieve the lightweight depth model. The experimental results show that on the actual data set collected from the project, the mAP reaches 82.1%, and the number of parameters is reduced by 8.5MB.
(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Jing Shi "Optimization and implementation of vehicle detection algorithm for tiny objects", Proc. SPIE 12800, Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023), 128000Q (11 October 2023); https://doi.org/10.1117/12.3004036
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Object detection

Target detection

Detection and tracking algorithms

Computer vision technology

Mathematical optimization

Visual process modeling

Artificial neural networks

Back to Top