Recently, 6DoF object pose estimation has become increasingly important for a broad range of applications in the fields of virtual reality, augmented reality, autonomous driving, and robotic operations. This task involves extracting the target area from the input data and subsequently determining the position and orientation of the objects. In recent years, many new advances have been made in pose estimation. However, existing reviews have the problem of only summarizing category-level or instance-level methods, and not comprehensively summarizing deep learning methods. This paper will provide a comprehensive review of the latest progress in 6D pose estimation to help researchers better understanding this area. In this study, the current methods about 6DoF object pose estimation are mainly categorized into two groups: instance-level and category-level groups, based on whether it is necessary to acquire the CAD model of the object. Recent advancements about learning-based 6DoF pose estimation methods are comprehensively reviewed. The study systematically explores the innovations and applicable scenarios of various methods. It provides an overview of widely used datasets, task metrics, and diverse application scenarios. Furthermore, state-of-the-art methods are compared across publicly accessible datasets, taking into account differences in input data types. Finally, we summarize the challenges of current tasks, methods for different applications, and future development directions.

In complex industrial environments, accurate recognition and localization of industrial targets are crucial. This study aims to improve the precision and accuracy of object detection in industrial scenarios by effectively fusing feature information at different scales and levels, and introducing edge detection head algorithms and attention mechanisms. We propose an improved YOLOv5-based algorithm for industrial object detection. Our improved algorithm incorporates the Crossing Bidirectional Feature Pyramid (CBiFPN), effectively addressing the information loss issue in multi-scale and multi-level feature fusion. Therefore, our method can enhance detection performance for objects of varying sizes. Concurrently, we have integrated the attention mechanism (C3_CA) into YOLOv5s to augment feature expression capabilities. Furthermore, we introduce the Edge Detection Head (EDH) method, which is adept at tackling detection challenges in scenes with occluded objects and cluttered backgrounds by merging edge information and amplifying it within the features. Experiments conducted on the modified ITODD dataset demonstrate that the original YOLOv5s algorithm achieves 82.11% and 60.98% on mAP@0.5 and mAP@0.5:0.95, respectively, with its precision and recall being 86.8% and 74.75%, respectively. The performance of the modified YOLOv5s algorithm on mAP@0.5 and mAP@0.5:0.95 has been improved by 1.23% and 1.44%, respectively, and the precision and recall have been enhanced by 3.68% and 1.06%, respectively. The results show that our method significantly boosts the accuracy and robustness of industrial target recognition and localization.

In most liquid crystal display (LCD) backlight modules (BLMs), diffuser plates (DPs) play the essential role in blurring the backlight. A common BLM consists of multiple superimposed optical films. In a vision-based automated assembly system, to ensure sufficient accuracy, each of the multiple cameras usually shoots a local corner of the DP and jointly estimates the target pose, guiding the robot to assemble the DP on the BLM. In general, DPs are typical of texture-less objects with simple shapes. Due to the image background of superimposed multilayer optical films, the robustness of the most common detection methods must be improved to meet industrial needs. To solve the above problem, a texture-less surface matching method based on gray-scale images was proposed. An augmented and normalized gray-scale vector represents the texture-less gray-scale surface in a low-dimensional space. The cosine distance is then used to calculate the similarity between the template and matching vectors, combined with shape-based matching (SBM); the proposed method can obtain high robustness when detecting DPs. An image database from actual production lines was used in the experiment. In comparative tests with the NCC, SBM, YOLOv5s, and YOLOv5x methods, our proposed method had the best precision at all confidence thresholds. Although recall was slightly inferior to SBM, the comprehensive evaluation F1-Score reached 0.826, significantly outperforming the other methods. Regarding localizing accuracy, our algorithm also performed best, reaching 5.7 pixels. Although the time consumption of a single prediction is about 0.6 s, it can still meet industrial needs. These experimental results show that the proposed method has high robustness in detecting DPs and is especially suitable for vision-based automatic assembly tasks in BLM.