An enhanced YOLOv5 based on Color Harmony Algorithm for object detection in Unmanned Aerial Vehicle captured Images

Abstract

Recent improvements in robotics and computer vision enable new camera-equipped drone applications. Aerial Object Detection (OD) is one. Despite recent advances, computer vision OD remains difficult. Due to UAVs' fast speed, different views, and fluctuating altitudes, objects in Unmanned Aerial Vehicle (UAV) photos are heterogeneous, fluctuate in size, and are dense, making OD challenging with existing algorithms. Existing object recognition algorithms perform worse on UAV images because OD in aerial images is more difficult than in ground-taken images. If a generic object detection technique is used to drone-captured images, its performance will be drastically degraded owing to the fact that varied surroundings with complicated background and the size of objects are at the core of this phenomena. In this work, an object detection model CHA-YOLOv5 is proposed. In the proposed system the detection module is optimized using the Color Harmony Algorithm, as it determines the prediction head from the available three prediction heads. CHA-YOLOv5 accurately predicts several bounding boxes per grid cell. The proposed model has been trained using several images from challenging contexts. The experimental results show that the objects are identified accurately using the proposed improved network model in this study. It achieved precision 98.675%, pecall 97.8023%, mAP 97.23%, F1 score 98.50%. Our system outperformed the YOLOV5, ResNet50, VGG19, and InceptionNet V3.

Refined single-stage object detection deep-learning technique for chilli leaf disease detection

“…where N class is the number of object classes, j is the threshold of IOU, and n th is the number of thresholds of IOU. 37 The F1-score is the harmonic mean of precision and recall and provides a single score that balances the two metrics. It is calculated as…”

“…mAP is a commonly used metric that combines precision and recall across a range of thresholds. It is calculated by averaging the precision values at different recall levels mAP=1Nclass∑j=1nthAPj,where Nclass is the number of object classes, j is the threshold of IOU, and nth is the number of thresholds of IOU 37 . The F1-score is the harmonic mean of precision and recall and provides a single score that balances the two metrics.…”

Improved Detection and Tracking of Objects Based on a Modified Deep Learning Model (YOLOv5)

“…The backbone extracts information from the input image [14]. The neck connects the head and the backbone [15]. The head represents the Yolo layer and is responsible for outputting detection results, including the category and location of the object [16].…”