Performance Evaluation of YOLOv5-based Custom Object Detection Model for Campus-Specific Scenario
Journal Title: International Journal of Experimental Research and Review - Year 2024, Vol 38, Issue 2
Abstract
This study evaluates the performance of a custom object detection model based on the YOLOv5 architecture, specifically tailored for autonomous electric vehicles. The model undergoes pre-processing using the Roboflow computer vision platform, which offers a wide range of tools for data pre-processing and model training. The experiments were conducted on a diverse dataset comprising various objects encountered in campus-specific driving scenarios, such as pedestrians, vehicles, buildings, and obstacles. The performance of the custom object detection model is assessed using standard metrics, including precision, recall, mean average precision (mAP), and intersection-over-union (IoU) at different thresholds. The training process was conducted in a controlled environment, resulting in a Precision of 0.851, a Recall of 0.831, and a mAP of 0.843. These metrics were analyzed to evaluate the YOLOv5-based custom object detection model's ability to detect and categorize objects accurately, its precision in predicting bounding boxes, and its capability to handle various object categories. We also examined the effects of different hyperparameters and data augmentation techniques on the model's performance, including variations in learning rate, batch size, and optimizer algorithms to determine their impact on accuracy and convergence. This analysis provided valuable insights into the model's strengths and weaknesses, highlighting areas for improvement and optimization. These findings are instrumental in developing and deploying advanced object detection systems to enhance the safety and reliability of autonomous electric vehicles.
Authors and Affiliations
Dontabhaktuni Jayakumar, Samineni Peddakrishna
Keywords
Related Articles
- EP ID EP734945
- DOI 10.52756/ijerr.2024.v38.005
- Views 49
- Downloads 0
Experimental Study on Mechanical Behaviour of Arhar-Reinforced Composites using GRA with PCA
The fiber composite plays a vital role in various applications in the current scenario. Natural fibers provide the desired advantages over synthetic fibers. Fiber composites deliver the exploration of durable, degradable...
The Effect of the Food Expression Art Therapy Group Counseling Program on the Interpersonal Relationship and Happiness of Prospective Early Childhood Teachers
This study aimed to determine the impact on the interpersonal relationships and happiness of prospective early childhood teachers by applying a group counseling program for food expression art therapy. Eight fourth-grade...
Meta Heuristic Algorithm Based Novel Dstatcom Architecture for Power Quality Improvement
Electric utility systems are increasingly favoured as local energy systems due to their ability to integrate renewable energy, improve energy efficiency, and enhance the resilience of the power grid. However, while these...
A mini-review to delineate the different roles of stem cells and Wnt signalling pathways in governing transdifferentiation towards neuronal lineage.
Mesenchymal stem cells are found to have the potential to differentiate into many lineages, thus regulating diverse signalling cascades. This unique property of stem cells, called trans differentiation/linear reprogrammi...
Improving Deposition Quality of Stellite Powder on Valve Seats by Optimized TIG Welding Parameters
The quality of the Stellite powder coated on these valve seats depends on the discharge profile and is crucial to the service length and quality of these seats, especially when called upon to work at their maximum capabi...