Fabrication progress detection for concrete T-girder based on improved YOLOv4

Large precast concrete girder plants have many processes, long cycles, and a large amount of data. This study proposes an improved YOLOv4 object detection algorithm with a spatio-temporal relationship to detect each fabrication process of precast concrete girders. It realises the fabrication information’s digitisation of traditional precast concrete girder plants. Initially, adding upsampling and convolution layers to the YOLOv4 base model enhances the algorithm’s feature extraction ability at different fabrication stages of precast concrete girders. Adopting the spatio-temporal relationship to determine the fabrication progress of precast concrete girders with identical features but at various fabrication stages. Finally, this research conducts an application analysis in an actual precast concrete girder plant. The analysis result indicated that the improved YOLOv4 algorithm significantly raises mAP and Average IOU in recognition. In addition, the spatio-temporal relationship effectively solves error detection problems caused by the similar appearance at different fabrication stages. This method provides practical support for digitising the fabrication data of traditional precast girder plants.