Carton dataset synthesis based on foreground texture replacement

One major impediment in rapidly deploying object detection models for industrial applications is the lack of large annotated datasets. Currently, in the e-commerce logistics industry, there is a Sacked Carton Dataset(SCD) that contains carton images from three scenarios such as comprehensive pharmaceutical logistics company(CPLC), e-commerce logistics company(ECLC), fruit market(FM). However, due to domain shift, the model trained with carton datasets from one of the three scenarios in SCD has poor generalization ability when applied to the rest scenarios. To solve this problem, a novel image synthesis method is proposed to replace the foreground texture of the source datasets with the foreground instance texture of the target datasets. This method can greatly augment the target datasets and improve the model's performance. We firstly propose a surfaces segmentation algorithm to identify the different surfaces of the carton instance. Secondly, a contour reconstruction algorithm is proposed to solve the problem of occlusion, truncation, and incomplete contour of carton instances. Finally, we use the Gaussian fusion algorithm to fuse the background from the source datasets with the foreground from the target datasets. In the experiments, our novel image synthesis method can largely boost AP by at least $4.3\%\sim6.5\%$ on RetinaNet and $3.4\%\sim6.8\%$ on Faster R-CNN for the target domain. And on the source domain, the performance AP can be improved by $1.7\%\sim2\%$ on RetinaNet and $0.9\%\sim1.5\%$ on Faster R-CNN. Code is available \href{https://github.com/hustgetlijun/RCAN}{here}.