Year: 2025
Type: conference-paper
Abstract: Object detection is essential for autonomous vehicle (AV) safety, underpinning tasks like path planning, collision avoidance, and motion prediction. This ongoing research presents preliminary findings from a concise survey of object detection methodologies, including image-based, 3D detection, and hybrid approaches. By reviewing performance metrics such as accuracy, speed, and robustness, it explores trade-offs among methods and identifies initial opportunities for optimization. Challenges such as computational demands, robustness in adverse conditions, and data diversity limitations are discussed alongside potential strategies like lightweight model optimization and multimodal sensor fusion. These preliminary insights aim to guide future research in developing scalable and efficient detection systems for safer AV deployment.
Source: ACM Southeast Conference (ACMSE)
Authors: Simran Devi, Hanieh Shabanian
Institution: Western New England University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4410192330