The occurrence of internal defects is inevitable in the casting process. It affects the reliability and durability of products and even gives rise to potential economic losses and security issues. Therefore, it appears essential to identify and eliminate defects in time. Deep learning algorithms can acquire more effective feature representation in complex scenes. Hence, a lightweight modified DeepLabV3+ algorithm is proposed with the following improvements. First, the ImageNet pre-trained MobileNetV2 is adopted as the backbone network to enhance the model feature extraction and improve the detection speed. Second, the atrous spatial pyramid pooling (ASPP) module is constructed for multi-scale feature fusion using atrous separable convolutions with different dilation rates. Third, the decoder is modified to fuse feature maps of different levels. Moreover, efficient channel attention modules are introduced to obtain more effective features and thus improve the defect edge segmentation effect. Last, a hybrid loss function of Focal Loss and Lovaszsoftmax Loss is used to reduce the influence of sample imbalance on model performance. The experimental results show that compared with the classical algorithms, the modified algorithm has higher accuracy and efficiency in the X-ray casting defect segmentation dataset CDSXray with less computational complexity.
At present, the object grasping system of robot based on vision is one of the research hotspots, and it has a broad application prospect in industry, especially in the part of sorting. The key technologies of this system include robot hand-eye calibration, grasping target detection, grasping path planning, etc. This paper provides an overview about the current status of these key technologies by collating relevant literature, including the four kinds of hand-eye calibration methods, deep learning based grasping target detection algorithms, and the advantages and disadvantages of three kinds of grasping path planning methods. In this paper, the key technologies of vision-based robot object grasping system are summarized and prospected, which can be helpful to researchers in related fields.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.