Volume 19, No. 2, 2022

Case Study: Performance Of Yolov 4 Is Better Than Yolov 3


Prof. Dr.Kamal Alaskar , Dr.Firoj A. Tamboli , Dr.Rajendra Jadhav , Mrs.Manjushri A Kadam

Abstract

In computer vision, there are so many applications and uses, one of which is object detection. Object detection is a subset of computer vision that is used to detect the presence, location, and type of objects in images. Object detection is also a combination of three functions; Object recognition, to find objects in an image, Object localization, to find where exactly in the image the objects are located, and Object classification, to detect what particular objects are in that image. There are lots of ways used to pick or grasp object through robotic hand but there are some hardly worked done with help the of Deep Learning approaches. To solve this issue, a solution is proposed which involves human strategies of picking up an object using Neural Network classifier. Classifier uses help of object detection model to detect object in environment and classifier classifies into picking strategy as per objects shape and orientation. Strategy detected by classifier can be used by soft hand as anticipatory action and reactive grasp. To increase accuracy number of primitive measures taken into consideration, our bounded and some of limitation are taken into mind while proposing architecture.


Pages: 2579-2590

Keywords: Object Detection, Deep learning, Grasping Strategies, Neural Network, Soft Hand.

Full Text