Evolution of YOLO-V5 Algorithm for Object Detection: Automated Detection of Library Books and Performace validation of Dataset

Karthi, M.; Muthulakshmi, V.; Priscilla, R.; Praveen, P; Vanisri, K

doi:10.1109/icses52305.2021.9633834

Cited by 67 publications

(28 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each text le contains one row per object, specifying the object's class and the bounding box coordinates relative to the image size. This structured dataset, enriched with annotations and properly formatted for YOLOv5, serves as the foundation for training the model to accurately detect and localize eggs in the poultry conveyor system [6].…”

Section: Methods and Techniquesmentioning

confidence: 99%

Application of Artificial Intelligence in Poultry Farming - Advancing Efficiency in Poultry Farming By Automating The Egg Counting Using Computer Vision System

Vinod,

Mohanty,

John

et al. 2023

Preprint

View full text Add to dashboard Cite

Counting eggs may seem like a simple task, but for poultry farms, it is a vital process that directly impacts productivity, inventory control, and overall output quality. However, the conventional manual counting methods are laborious, time-consuming, and prone to human errors. This research presents a ground-breaking computer imaging system designed to automate egg detection and counting, utilizing the remarkable potential of Computer Vision and Artificial Intelligence (AI) techniques. The primary objective is to develop a robust and reliable system capable of real-time identification and enumeration of eggs within poultry houses. Strategically positioned cameras capture images, providing a unique perspective into the poultry environment. State-of-the-art computer vision algorithms, including advanced object detection methods like Faster Regions with Convolutional Neural Networks (Faster R-CNN) or You Only Look Once (YOLO), accurately identify eggs within the images using cutting-edge deep learning models. By integrating AI techniques, the system enhances accuracy and reliability, while continuously learning from vast amounts of data. This transformative automation eliminates labour-intensive manual counting, offering a dependable, efficient, and cost-effective solution while reducing both time and labour requirements and minimizing human errors. Moreover, the automated system enables real-time data collection, facilitating data-driven decision-making in the poultry industry. Through the integration of cutting-edge computer vision algorithms and AI techniques, the system provides an accurate, efficient, and reliable solution to optimize production processes, enhance inventory control, and ensure high-quality outputs. This work contributes to the ongoing technological advancements in the poultry industry, ultimately improving productivity, and sustainability, and enabling data-driven decision-making.

show abstract

Section: Methods and Techniquesmentioning

confidence: 99%

Application of Artificial Intelligence in Poultry Farming - Advancing Efficiency in Poultry Farming By Automating The Egg Counting Using Computer Vision System

Vinod,

Mohanty,

John

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…While the robot moves towards its goal, it may detect a net using its camera. We can apply deep neural networks, such as YOLOv5 [ 19 ], for underwater net detection. Note that underwater net detection under camera measurements is not our novel contribution.…”

Section: Net Avoidance Controlsmentioning

confidence: 99%

“…As deep neural networks, one can use the R-CNN family, which includes Fast R-CNN [ 15 ], Faster R-CNN [ 16 ], and Mask R-CNN [ 17 ], which have both object detection and instance segmentation capabilities. As state-of-the-art deep neural networks, one can use You Only Look Once (YOLO) algorithms [ 18 , 19 , 20 ], which have been widely used for object detection and bounding box generation.…”

Section: Introductionmentioning

confidence: 99%

“…As far as we know, our paper is unique in proposing how to make the robot reach its goal while avoiding fishing nets detected using camera sensors. Using the camera measurements, we can apply deep neural networks, such as YOLOv5 [ 19 ], which compute an image bounding box containing the net. Based on the net’s bounding box, we develop novel reactive control laws for avoiding collision with the detected net.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Camera-Based Net Avoidance Controls of Underwater Robots

Kim

2024

Sensors

View full text Add to dashboard Cite

Fishing nets are dangerous obstacles for an underwater robot whose aim is to reach a goal in unknown underwater environments. This paper proposes how to make the robot reach its goal, while avoiding fishing nets that are detected using the robot’s camera sensors. For the detection of underwater nets based on camera measurements of the robot, we can use deep neural networks. Passive camera sensors do not provide the distance information between the robot and a net. Camera sensors only provide the bearing angle of a net, with respect to the robot’s camera pose. There may be trailing wires that extend from a net, and the wires can entangle the robot before the robot detects the net. Moreover, light, viewpoint, and sea floor condition can decrease the net detection probability in practice. Therefore, whenever a net is detected by the robot’s camera, we make the robot avoid the detected net by moving away from the net abruptly. For moving away from the net, the robot uses the bounding box for the detected net in the camera image. After the robot moves backward for a certain distance, the robot makes a large circular turn to approach the goal, while avoiding the net. A large circular turn is used, since moving close to a net is too dangerous for the robot. As far as we know, our paper is unique in addressing reactive control laws for approaching the goal, while avoiding fishing nets detected using camera sensors. The effectiveness of the proposed net avoidance controls is verified using simulations.

show abstract

“…One-stage detector are faster and can achieve good accuracy for our application. At the time of writing, newly developed YOLOv5 [7] has been reported to have best performance in accuracy and framerate [8]. Therefore, all network sizes of the YOLOv5 algorithm (YOLOv5s, -m, -l, -x) are selected and will be evaluated further in section III.…”

Section: A Detectionmentioning

confidence: 99%

Visual Drone Detection and Tracking for Autonomous Operation from Maritime Vessel

Halleux

Tien-Thanh

Hamesse

et al. 2022

2022 International Symposium on Measurement and Control in Robotics (ISMCR)

View full text Add to dashboard Cite

To allow incorporation of autonomous Unmanned Aerial Vehicles (UAV's/drones) into maritime military operations, it is critical to be able to accurately localize the UAV with respect to the moving maritime vessel during the take-off and landing phases. This work addresses the study and implementation of a visual detection, tracking and threedimensional positioning method for a specific drone from a moving maritime vessel. The YOLOv5 detector and the OceanPlus tracker have been trained on a custom dataset with good performance in accuracy and processing time. The drone's position with respect to the vessel is estimated by applying stereo triangulation to the centres of the bounding boxes returned by the object detectors and trackers. The performance of the proposed positioning method was evaluated in a realistic simulated environment in the Unreal Game Engine. The proposed method allows detection, tracking, and positioning of a target drone at ranges exceeding 100m while achieving positioning errors below 10cm during landing phases.

show abstract

Evolution of YOLO-V5 Algorithm for Object Detection: Automated Detection of Library Books and Performace validation of Dataset

Cited by 67 publications

References 6 publications

Application of Artificial Intelligence in Poultry Farming - Advancing Efficiency in Poultry Farming By Automating The Egg Counting Using Computer Vision System

Application of Artificial Intelligence in Poultry Farming - Advancing Efficiency in Poultry Farming By Automating The Egg Counting Using Computer Vision System

Camera-Based Net Avoidance Controls of Underwater Robots

Visual Drone Detection and Tracking for Autonomous Operation from Maritime Vessel

Contact Info

Product

Resources

About