Fruit ripeness identification using YOLOv8 model

Abstract

Deep learning-based visual object detection is a fundamental aspect of computer vision. These models not only locate and classify multiple objects within an image, but they also identify bounding boxes. The focus of this paper's research work is to classify fruits as ripe or overripe using digital images. Our proposed model extracts visual features from fruit images and analyzes fruit peel characteristics to predict the fruit's class. We utilize our own datasets to train two "anchor-free" models: YOLOv8 and CenterNet, aiming to produce accurate predictions. The CenterNet network primarily incorporates ResNet-50 and employs the deconvolution module DeConv for feature map upsampling. The final three branches of convolutional neural networks are applied to predict the heatmap. The YOLOv8 model leverages CSP and C2f modules for lightweight processing. After analyzing and comparing the two models, we found that the C2f module of the YOLOv8 model significantly enhances classification results, achieving an impressive accuracy rate of 99.5%.

RDD-YOLO: Road Damage Detection Algorithm Based on Improved You Only Look Once Version 8

“…In 2017, Joseph Redmon et al proposed YOLOv2 [18]. It incorporates batch [16] and analyzes whether each border is the position and confidence of the detected object [17]. YOLOv1 has a small computational load and fast runtime, but it is less effective in detecting small targets and requires accuracy improvement.…”

“…Figure2shows the evolution timeline of the YOLO algorithm. YOLOv1, the initial version of the YOLO algorithm, was introduced by Joseph Redmon et al at the University of Washington in 2015 grid[16] and analyzes whether each border is the position and confidence of the detected object[17]. YOLOv1 has a small computational load and fast runtime, but it is less effective in detecting small targets and requires accuracy improvement.…”

Synthetic Meets Authentic: Leveraging Text-to-Image Generated Datasets for Apple Detection in Orchard Environments

“…In agriculture, such technology are crucial of efficient and effective field operations, including crop health monitoring, pest control, irrigation optimization, nutrient deficiency assessment, and automated harvesting [1], [2]. Specifically, in apple orchards, computer-vision based apple detection becomes crucial as it enables various automated operations in orchards including but not limited to precision apple harvesting [3], disease detection [4], [5], yield forecasting [6], [7], growth tracking and analysis [8], pest recognition [9], color-based fruit grading [10], [11], size-based fruit sorting, ripeness evaluation [12], [13], health monitoring , and robotic guidance, and orchard mapping for robot navigation [14].…”

Road damage detection and classification using deep neural networks

“…In this paper, we present a refined road damage detection algorithm that capitalizes on the enhanced capabilities of the YOLOv8 architecture [11]. This algorithm is specifically designed for embedded systems, offering a substantial improvement in the detection and analysis of road surface imperfections.…”