Design of a laboratory scale Automatic Optical Inspection prototype system for scanning of conveyor belt surfaces — A case study

Banerjee, P.; Chakravarty, Debashish; Samanta, Biswanath

doi:10.1016/j.measurement.2023.113342

Cited by 2 publications

(1 citation statement)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods include X-ray detection, the built-in induction coil method, and machine vision-based methods [5,6]. Due to the challenging working conditions of conveyor belts, including uneven lighting, high humidity, and dust accumulation over extended periods, methods for image analysis based on visible light, infrared light, and auxiliary laser [7][8][9] are limited to laboratory environments and are challenging to implement effectively in real-world scenarios. Deep learning-based vision detection methods [10] stand out due to their strong ability to handle demanding environmental factors, real-time performance, cost-effectiveness, and robustness.…”

Section: Introductionmentioning

confidence: 99%

HLG-YOLOv7: small object detection in conveyor belt damage based on leveraging hybrid local and global features

Wang,

Yue,

Sun

et al. 2024

Eng. Res. Express

View full text Add to dashboard Cite

In the industrial production process, the detection of conveyor belt damage plays a crucial role in ensuring the stable operation of the transportation system. To tackle the issues of significant changes in damage size, missed detections, and poor detection ability of small-size objects in conveyor belt surface damage detection, an improved HLG-YOLOv7 (Hybrid Local and Global Features Network) conveyor belt surface defect detection algorithm is proposed. Firstly, Next-VIT is employed as the backbone network to fully extract local and global features of the damage, enhancing the model’s ability to extract features of different-sized damages. Additionally, to deeply utilize the extracted local and global features, the Explicit Visual Center (EVC) feature fusion module is introduced to obtain comprehensive and discriminative feature representations, further enhancing the detection capability of small objects. Lastly, a lightweight neck structure is designed using GSConv to reduce the complexity of the model. Experimental results demonstrate that the proposed method has better small object detection performance compared to existing methods. The improved algorithm achieves mAP and F1 scores of 96.24% and 97.15%, respectively, with an FPS of 28.2.

show abstract