Paper
8 May 2022 Research and implementation of industrial rebar inventory mobile application program based on YOLOv5 algorithm
Kaiwei Deng, Lizhi Liu
Author Affiliations +
Proceedings Volume 12249, 2nd International Conference on Internet of Things and Smart City (IoTSC 2022); 122491E (2022) https://doi.org/10.1117/12.2636466
Event: 2022 2nd International Conference on Internet of Things and Smart City (IoTSC 2022), 2022, Xiamen, China
Abstract
In view of the current construction site, the steel bar inventory work is still using manpower counting method, the process is cumbersome, time-consuming and inefficient. YOLOv5s algorithm was used to train the rebar counting lightweight model, Mosaic data was used to enhance the data set, and CSP structure was used to enhance the feature extraction ability of the model. Compared with the existing mainstream lightweight models such as YOLOV3-Tiny and Mobilenet-SSD, the mAP of YOLOv5s reached 0.994. In order to overcome the impact of complex environment and better apply to smart site, the model was deployed to Mobile devices using Pytorch Mobile framework. In the test set, the counting accuracy of the mobile application of reabar inventory is above 0.98, and the detection effect is equivalent to that of the server. Experimental results show that YOLOV5s intelligent reabr counting model deployed to mobile terminal has good detection accuracy and accuracy.
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Kaiwei Deng and Lizhi Liu "Research and implementation of industrial rebar inventory mobile application program based on YOLOv5 algorithm", Proc. SPIE 12249, 2nd International Conference on Internet of Things and Smart City (IoTSC 2022), 122491E (8 May 2022); https://doi.org/10.1117/12.2636466
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Performance modeling

Data modeling

Evolutionary algorithms

Feature extraction

Process modeling

Target detection

Image fusion

Back to Top