Orchard environment pedestrian detection method based on improved YOLOv3

Abstract

The invention discloses an orchard environment pedestrian detection method based on improved YOLOv3. The method comprises the steps: S1, collecting images in an orchard environment and preprocessed, and making an orchard pedestrian sample set; s2, utilizing a K-means clustering algorithm to generate an anchor box number to calculate pedestrian candidate boxes; s3, adding a finer feature extractionlayer to the YOLOv3 network, and increasing the detection output of the network in a large-scale feature layer to obtain an improved network model YOLO-Z; s4, inputting the training set into a YOLO-Znetwork to carry out various environment training, and then storing a weight file of the training set; and S5, introducing a Kalman filtering algorithm and carrying out corresponding improvement to improve the robustness of the model, solve the problem of missing detection and improve the detection speed. According to the invention, the problems of low pedestrian real-time detection speed and lowaccuracy in an orchard environment are solved, multi-task training is realized, and pedestrian detection speed and precision in the orchard environment are ensured.

Description

technical field [0001] The invention relates to a pedestrian detection method in an orchard environment based on improved YOLOv3, aiming at pedestrian detection by an unmanned agricultural machine in an orchard environment, and belongs to the technical fields of deep learning and pedestrian detection. Background technique [0002] With the rapid development of artificial intelligence, agricultural intelligent equipment has also entered a historic moment, and unmanned agricultural machinery is the top priority of agricultural intelligent equipment. In the field operation of unmanned agricultural machines, obstacle detection is the primary problem, and pedestrian detection is even more crucial. At present, the commonly used methods for pedestrian detection include methods based on motion characteristics, methods based on shape information, methods based on pedestrian models, methods based on stereo vision, methods based on neural networks, methods based on wavelets and support...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above pedestrian detection requirements for intelligent unmanned agricultural machinery in the orchard environment, the present invention provides a pedestrian detection method in the orchard environment based on improved YOLOv3, which regards detection as a regression problem and directly uses the convolutional network structure to process the entire image , simultaneously predicting the detected category and location

Images