关键词: 铸管字符检测, 背景模糊, Cascade RCNN, ResNeSt

Abstract: Due to the issues of blurred background,small character areas,inconsistent engraving positions,and paint occlusion in the images of cast pipe characters collected from industrial sites,the existing models struggle to meet the detection accuracy requirements of industrial environments.To address these issues,an improved Cascade RCNN algorithm for cast pipe character detection is proposed.Firstly,improvements are made to the feature pyramid by introducing the Small Target Enhancement Feature Pyramid Networks (STE-FPN),which utilize the feature enhancement capability of multi-scale feature fusion to enrich the feature information of small target characters on cast pipes.Secondly,the Self-Calibrated/Pooling ResNeSt (SCP-ResNeSt) is introduced as the feature extraction network,utilizing self-calibrated convolutions and pooling operations to enhance the efficiency of extracting complex background features of cast pipe characters.Lastly,improvements are made to the cascade structure by introducing a Mask branch structure,which adaptively detects character areas and removes interference regions,thus optimizing the detection results.The improved algorithm was tested on the cast pipe dataset,and Mean Average Precision (mAP) is 99.1%,which increased the precision by 2.3% compared to the Cascade RCNN.The precision shows that the improved performance is superior to the original algorithm.

Key words: character detection of cast pipes, blurred background, Cascade RCNN, ResNeSt