{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T13:02:51Z","timestamp":1772715771150,"version":"3.50.1"},"reference-count":28,"publisher":"Emerald","issue":"4","license":[{"start":{"date-parts":[[2022,2,15]],"date-time":"2022-02-15T00:00:00Z","timestamp":1644883200000},"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":[[2022,6,1]]},"abstract":"<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Purpose<\/jats:title>\n<jats:p>Scattered parts are laid randomly during the manufacturing process and have difficulty to recognize and manipulate. This study aims to complete the grasp of the scattered parts by a manipulator with a camera and learning method.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Design\/methodology\/approach<\/jats:title>\n<jats:p>In this paper, a cascaded convolutional neural network (CNN) method for robotic grasping based on monocular vision and small data set of scattered parts is proposed. This method can be divided into three steps: object detection, monocular depth estimation and keypoint estimation. In the first stage, an object detection network is improved to effectively locate the candidate parts. Then, it contains a neural network structure and corresponding training method to learn and reason high-resolution input images to obtain depth estimation. The keypoint estimation in the third step is expressed as a cumulative form of multi-scale prediction from a network to use an red green blue depth (RGBD) map that is acquired from the object detection and depth map estimation. Finally, a grasping strategy is studied to achieve successful and continuous grasping. In the experiments, different workpieces are used to validate the proposed method. The best grasping success rate is more than 80%.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Findings<\/jats:title>\n<jats:p>By using the CNN-based method to extract the key points of the scattered parts and calculating the possibility of grasp, the successful rate is increased.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Practical implications<\/jats:title>\n<jats:p>This method and robotic systems can be used in picking and placing of most industrial automatic manufacturing or assembly processes.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Originality\/value<\/jats:title>\n<jats:p>Unlike standard parts, scattered parts are randomly laid and have difficulty recognizing and grasping for the robot. This study uses a cascaded CNN network to extract the keypoints of the scattered parts, which are also labeled with the possibility of successful grasping. Experiments are conducted to demonstrate the grasping of those scattered parts.<\/jats:p>\n<\/jats:sec>","DOI":"10.1108\/ir-10-2021-0236","type":"journal-article","created":{"date-parts":[[2022,2,12]],"date-time":"2022-02-12T05:39:50Z","timestamp":1644644390000},"page":"645-657","source":"Crossref","is-referenced-by-count":10,"title":["A cascaded CNN-based method for monocular vision robotic grasping"],"prefix":"10.1108","volume":"49","author":[{"given":"Xiaojun","family":"Wu","sequence":"first","affiliation":[]},{"given":"Peng","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jinghui","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Yunhui","family":"Liu","sequence":"additional","affiliation":[]}],"member":"140","published-online":{"date-parts":[[2022,2,15]]},"reference":[{"key":"key2022053115391708600_ref001","first-page":"730","article-title":"Single-image depth perception in the wild","year":"2016"},{"key":"key2022053115391708600_ref002","first-page":"1610","article-title":"Xception: deep learning with depthwise separable convolutions","year":"2017","journal-title":"arXiv Preprint"},{"key":"key2022053115391708600_ref003","first-page":"379","article-title":"R-FCN: object detection via region-based fully convolutional networks","year":"2016"},{"key":"key2022053115391708600_ref004","first-page":"2650","article-title":"Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture","year":"2015"},{"key":"key2022053115391708600_ref005","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume-title":"Advances in Neural Information Processing Systems (NIPS)","year":"2014"},{"key":"key2022053115391708600_ref006","first-page":"6602","article-title":"Unsupervised monocular depth estimation with left-right consistency","year":"2017"},{"issue":"5","key":"key2022053115391708600_ref007","first-page":"688","article-title":"Practical aspects of detection and grasping objects by a mobile manipulating robot","volume":"48","year":"2021","journal-title":"Industrial Robot"},{"key":"key2022053115391708600_ref008","first-page":"89","article-title":"Pulling things out of perspective","year":"2014","journal-title":"2014 IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"key2022053115391708600_ref009","first-page":"239","article-title":"Deeper depth prediction with fully convolutional residual networks","year":"2016"},{"issue":"4\/5","key":"key2022053115391708600_ref010","first-page":"705","article-title":"Deep learning for detecting robotic grasps","volume":"34","year":"2015","journal-title":"The International Journal of Robotics Research"},{"issue":"1","key":"key2022053115391708600_ref011","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1108\/IR-01-2020-0005","article-title":"Target dynamic grasping during mobile robot movement based on learning methods","volume":"48","year":"2021","journal-title":"Industrial Robot: The International Journal of Robotics Research and Application"},{"key":"key2022053115391708600_ref012","article-title":"Light-head R-CNN: in defense of two-stage object detector","year":"2017"},{"key":"key2022053115391708600_ref013","first-page":"936","article-title":"Feature pyramid networks for object detection","year":"2017"},{"key":"key2022053115391708600_ref014","article-title":"Receptive field block net for accurate and fast object detection","year":"2017"},{"key":"key2022053115391708600_ref015","article-title":"SSD: single shot multibox detector","volume-title":"Computer Vision \u2013 ECCV 2016. Lecture Notes in Computer Science","year":"2016"},{"issue":"26","key":"key2022053115391708600_ref016","doi-asserted-by":"crossref","first-page":"aau4984","DOI":"10.1126\/scirobotics.aau4984","article-title":"Learning ambidextrous robot grasping policies","volume":"4","year":"2019","journal-title":"Science Robotics"},{"key":"key2022053115391708600_ref017","first-page":"1957","article-title":"Dex-Net 1.0: a cloud-based network of 3D objects for robust grasp planning using a multi-armed bandit model with correlated rewards","year":"2016"},{"key":"key2022053115391708600_ref018","article-title":"Closing the loop for robotic grasping: a real-time, generative grasp synthesis approach","year":"2018"},{"issue":"2\/3","key":"key2022053115391708600_ref019","first-page":"183","article-title":"Learning robust, real-time, reactive robotic grasping","volume":"39","year":"2020","journal-title":"The International Journal of Robotics Research"},{"key":"key2022053115391708600_ref020","first-page":"3406","article-title":"Supersizing self-supervision: learning to grasp from 50K tries and 700 robot hours","year":"2016"},{"key":"key2022053115391708600_ref022","unstructured":"Redmon, J. and Farhadi, A. (2018), \u201cYolov3: An incremental improvement\u201d, Technical Report."},{"key":"key2022053115391708600_ref021","first-page":"779","article-title":"You only look once: unified, real-time object detection","year":"2016"},{"issue":"6","key":"key2022053115391708600_ref023","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","volume":"39","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"2","key":"key2022053115391708600_ref024","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1177\/0278364907087172","article-title":"Robotic grasping of novel objects using vision","volume":"27","year":"2008","journal-title":"The International Journal of Robotics Research"},{"key":"key2022053115391708600_ref025","article-title":"Indoor segmentation and support inference from RGBD images","volume-title":"Computer Vision \u2013 ECCV 2012, Lecture Notes in Computer Science","year":"2012"},{"key":"key2022053115391708600_ref026","first-page":"1175","article-title":"A vision-based robotic grasping system using deep learning for 3d object recognition and pose estimation","year":"2013"},{"issue":"64","key":"key2022053115391708600_ref027","article-title":"A CNN-based grasp planning method for random picking of unknown objects with a vacuum gripper","volume":"103","year":"2021","journal-title":"Journal of Intelligent and Robotic Systems"},{"key":"key2022053115391708600_ref028","first-page":"4203","article-title":"Single-Shot refinement neural network for object detection","year":"2018"}],"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-10-2021-0236\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IR-10-2021-0236\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T21:40:14Z","timestamp":1753393214000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/ir\/article\/49\/4\/645-657\/432252"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,15]]},"references-count":28,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2022,2,15]]},"published-print":{"date-parts":[[2022,6,1]]}},"alternative-id":["10.1108\/IR-10-2021-0236"],"URL":"https:\/\/doi.org\/10.1108\/ir-10-2021-0236","relation":{},"ISSN":["0143-991X","0143-991X"],"issn-type":[{"value":"0143-991X","type":"print"},{"value":"0143-991X","type":"print"}],"subject":[],"published":{"date-parts":[[2022,2,15]]}}}