{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T17:23:24Z","timestamp":1754155404576,"version":"3.41.2"},"reference-count":26,"publisher":"Emerald","issue":"1","license":[{"start":{"date-parts":[[2021,9,9]],"date-time":"2021-09-09T00:00:00Z","timestamp":1631145600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IR"],"published-print":{"date-parts":[[2022,1,3]]},"abstract":"<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Purpose<\/jats:title>\n<jats:p>Robot automatic grasping has important application value in industrial applications. Recent works have explored on the performance of deep learning for robotic grasp detection. They usually use oriented anchor boxes (OABs) as detection prior and achieve better performance than previous works. However, the parameters of their loss belong to different coordinates, this may affect the regression accuracy. This paper aims to propose an oriented regression loss to solve the problem of inconsistency among the loss parameters.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Design\/methodology\/approach<\/jats:title>\n<jats:p>In the oriented loss, the center coordinates errors between the ground truth grasp rectangle and the predicted grasp rectangle rotate to the vertical and horizontal of the OAB. And then the direction error is used as an orientation factor, combining with the errors of the rotated center coordinates, width and height of the predicted grasp rectangle.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Findings<\/jats:title>\n<jats:p>The proposed oriented regression loss is evaluated on the YOLO-v3 framework to the grasp detection task. It yields state-of-the-art performance with an accuracy of 98.8% and a speed of 71 frames per second with GTX 1080Ti on Cornell datasets.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Originality\/value<\/jats:title>\n<jats:p>This paper proposes an oriented loss to improve the regression accuracy of deep learning for grasp detection. The authors apply the proposed deep grasp network to the visual servo intelligent crane. The experimental result indicates that the approach is accurate and robust enough for real-time grasping applications.<\/jats:p>\n<\/jats:sec>","DOI":"10.1108\/ir-02-2021-0041","type":"journal-article","created":{"date-parts":[[2021,9,7]],"date-time":"2021-09-07T04:19:26Z","timestamp":1630988366000},"page":"160-167","source":"Crossref","is-referenced-by-count":0,"title":["Accurate grasp detection learning using oriented regression loss"],"prefix":"10.1108","volume":"49","author":[{"given":"Xuan","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hancheng","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingkui","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"140","published-online":{"date-parts":[[2021,9,9]]},"reference":[{"year":"2019","key":"key2021123108213338400_ref001","article-title":"Densely supervised grasp detector(DSGD)"},{"issue":"3","key":"key2021123108213338400_ref002","doi-asserted-by":"crossref","first-page":"57","DOI":"10.3390\/mti2030057","article-title":"Review of deep learning methods in robotic grasp detection","volume":"2","year":"2018","journal-title":"Multimodal Technologies and Interaction"},{"issue":"4","key":"key2021123108213338400_ref003","doi-asserted-by":"crossref","first-page":"3355","DOI":"10.1109\/LRA.2018.2852777","article-title":"Real-world multi-object, multi-grasp detection","volume":"3","year":"2018","journal-title":"IEEE Robotics and Automation Letters"},{"key":"key2021123108213338400_ref004","unstructured":"Cornell grasping dataset, (2013) available at: http:\/\/pr.cs.cornell.edu\/grasping\/rectdata\/data.php (accessed 09 January 2017)."},{"issue":"3","key":"key2021123108213338400_ref005","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","year":"1995","journal-title":"Machine Learning"},{"year":"2020","key":"key2021123108213338400_ref006","article-title":"Optimizing correlated graspability score and grasp regression for better grasp prediction"},{"key":"key2021123108213338400_ref007","first-page":"2261","article-title":"Densely connected convolutional networks","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","year":"2017"},{"key":"key2021123108213338400_ref008","first-page":"580","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","year":"2014"},{"first-page":"1609","article-title":"A hybrid deep architecture for robotic grasp detection","year":"2017","key":"key2021123108213338400_ref009"},{"key":"key2021123108213338400_ref010","first-page":"658","article-title":"Generalized intersection over union: a metric and a loss for bounding box regression","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","year":"2019"},{"key":"key2021123108213338400_ref011","first-page":"770","article-title":"Deep residual learning for image recognition","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","year":"2016"},{"key":"key2021123108213338400_ref012","first-page":"3304","article-title":"Efficient grasping from RGBD images: learning using a new rectangle representation","volume-title":"IEEE International Conference Robotics and Automation (ICRA)","year":"2011"},{"first-page":"7300","article-title":"A single Multi-Task deep neural network with Post-Processing for object detection with reasoning and robotic grasp detection","year":"2020","key":"key2021123108213338400_ref013"},{"key":"key2021123108213338400_ref014","first-page":"6517","article-title":"YOLO9000: better, faster, stronger","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","year":"2017"},{"year":"2018","key":"key2021123108213338400_ref015","article-title":"YOLOv3: an incremental improvement"},{"key":"key2021123108213338400_ref016","first-page":"779","article-title":"You only look once: unified, real-time object detection","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","year":"2015"},{"issue":"6","key":"key2021123108213338400_ref017","first-page":"1137","article-title":"FasterR-CNN: towards real-time object detection with region proposal networks","volume":"39","year":"2015","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"key2021123108213338400_ref018","doi-asserted-by":"crossref","first-page":"101963","DOI":"10.1016\/j.rcim.2020.101963","article-title":"A novel robotic grasp detection method based on region proposal networks","volume":"65","year":"2020","journal-title":"Robotics and Computer-Integrated Manufacturing"},{"year":"2019","key":"key2021123108213338400_ref019","article-title":"Antipodal robotic grasping using generative residual convolutional neural network"},{"issue":"3","key":"key2021123108213338400_ref020","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1364\/JOSAA.34.000415","article-title":"Vision-based technique for circle detection and measurement using lookup table and bitwise center accumulator","volume":"34","year":"2017","journal-title":"Journal of the Optical Society of America A"},{"first-page":"4768","article-title":"ROI-based robotic grasp detection for object overlapping scenes","year":"2019","key":"key2021123108213338400_ref021"},{"first-page":"1","article-title":"A Real-Time robotic grasping approach with oriented anchor box","year":"2019","key":"key2021123108213338400_ref022"},{"key":"key2021123108213338400_ref023","first-page":"12993","article-title":"Distance-IoU loss: faster and better learning for bounding box regression","volume-title":"International Conference on Artificial Intelligence","year":"2020"},{"first-page":"7223","article-title":"Fully convolutional grasp detection network with oriented anchor box","year":"2018","key":"key2021123108213338400_ref024"},{"first-page":"1316","article-title":"Real-time grasp detection using convolutional neural networks","year":"2015","key":"key2021123108213338400_ref025"},{"year":"2014","key":"key2021123108213338400_ref026","article-title":"Very deep convolutional networks for Large-Scale image recognition"}],"container-title":["Industrial Robot: the international journal of robotics research and application"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IR-02-2021-0041\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IR-02-2021-0041\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T21:38:29Z","timestamp":1753393109000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/ir\/article\/49\/1\/160-167\/183830"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,9]]},"references-count":26,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,9,9]]},"published-print":{"date-parts":[[2022,1,3]]}},"alternative-id":["10.1108\/IR-02-2021-0041"],"URL":"https:\/\/doi.org\/10.1108\/ir-02-2021-0041","relation":{},"ISSN":["0143-991X","0143-991X"],"issn-type":[{"type":"print","value":"0143-991X"},{"type":"print","value":"0143-991X"}],"subject":[],"published":{"date-parts":[[2021,9,9]]}}}