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 45
- Downloads 0
Isolation, Identification and in-Silico Characterization of Bioactive Peptide from the Venom Sac of Conus inscriptus
Nature has been the source of new medications since ancient times, and at least half of all commercialised pharmaceuticals have been made from renewable resources to treat various illnesses, including pain, inflammation,...
Formulation and Evaluation of Polyherbal Emulgel
The foible of allopathic medicines has resulted in adopting herbal plants that have been proven cost-effective with fewer adverse effects. Thus, the evaluation of the potential of herbal plants for the formulation of inn...
Fusion of Wavelet Features and Gabor Features for SVM-based Iris Verification
Iris verification now become increasingly prominent in biometric-based person verification systems. It has gained a significant role in biometric systems due to its stability, high uniqueness, contactless and non-invasiv...
Creating Urban Green Spaces (UGS) in Educational Institutions: A pilot project in Gurudas College, Kolkata-700054, West Bengal, India
Urban green spaces (UGS) supply ecosystem services such as biodiversity, climate regulation and other benefits. Urban green spaces are essential for the quality of life, health, and wellbeing of citizens. Urban green spa...
Spatial Analysis of Female Literacy in Religious Minorities of Uttar Pradesh, India
This study is related to the district-wise spatial analysis of female literacy in religious minorities of Uttar Pradesh. Analysis is based on district level secondary data obtained from the census of India (census report...