Method for identifying sheltered and overlapped fruits for picking robot

Abstract

The invention relates to a method for identifying sheltered and overlapped fruits for a picking robot, which belongs to the field of image identification, proposes a Dense-TRH-YOLO model, fuses a Denseblock module into a backbone network on the basis of YOLOv5, creates a segment path from an early stage layer to a later stage layer, and fuses a Transfomer module into the model, thereby improving semantic distinguishability and reducing category confusion. The method comprises the following steps of: firstly, extracting image features of each layer through a Unit + +-PAN neck structure, and finally, replacing a CIOU of an original model with an Officient IOU Loss loss function to carry out frame regression so as to output a detection frame position and classification confidence, respectively calculating a width-height difference value on the basis of the CIOU so as to replace an aspect ratio, and introducing Focal Loss to solve the problem of difficult and easy sample imbalance.

Description

technical field [0001] The invention belongs to the field of image recognition, and relates to an occlusion and overlapping fruit recognition method for picking robots. Background technique [0002] Harvesting fruit is very labor-intensive and time-consuming. With the development of artificial intelligence, much of this work could be replaced by harvesting robots. Harvesting with a robot is a two-step process. First, use a computer vision system for fruit detection. Secondly, according to the detection results, the robot is guided to pick the fruit. Among these two steps, fruit detection is the most critical and challenging. It not only determines the subsequent operation of the manipulator, but also determines the detection accuracy. The complex conditions and unstructured environment make this task very challenging. [0003] For fruit recognition and classification, various traditional visual detection methods are used to segment or locate fruit images. Nowadays, the...

AI Technical Summary

Problems solved by technology

[0004] In view of this, the purpose of the present invention is to provide a method for occlusion and overlapping fruit recognition for picking robots, which solves the problem of traditional target detection being easily affected by complex backgrounds and the serious occlusion and overlapping fruits in an unstructured environment. Detection and false detection, using the improved model Dense-TRU-YOLO based on the latest YOLOv5 network, reduces a large number of model parameters while maintaining accuracy, overcomes the large parameters of the general deep learning neural network model, the large amount of calculation, Disadvantages such as long calculation time, high requirements for computer hardware, and insufficient recognition accuracy

Images