Progress in multi-object detection models: a comprehensive survey

• Published in: Multimedia tools and applications Vol. 82; no. 15; pp. 22405 - 22439
• Main Authors: Balakrishna, Sivadi, Mustapha, Ahmad Abubakar
• Format: Journal Article
• Language: English
• Published: New York Springer US 01-06-2023; Springer Nature B.V
• Subjects: Algorithms; Brain; Classification; Computer Communication Networks; Computer Science; Data Structures and Information Theory; Deep learning; Multimedia; Multimedia Information Systems; Neural networks; Object recognition; Occlusion; Recommender systems; Sensors; Special Purpose and Application-Based Systems; Telematics; Deep learning; Research directions; Models; Multi-object detection; DPRS; Challenges
• ISSN: 1380-7501; 1573-7721
• DOI: 10.1007/s11042-022-14131-0

Deep learning-based object detection has become popular due to its strong learning ability and advantages in dealing with occlusion, scale transformation, and context changes. In recent years, it has become a research hotspot. This paper presents the current Deep Learning models from Generic and Salient detection models ranging from one-stage to two-stage for multi-object detection in various applications. Nevertheless, we also examined the advantages and some drawbacks of those models. Furthermore, challenges such as variation in object scales, computation time, illumination differing from various applications, and promising research directions of Deep Learning models are discussed. Finally, we proposed Dense PRediction Simplified (DPRS) based on the YOLO model. Backbones play a vital role in enhancing the performance of detection models, and efficient Backbone architecture will be fused to achieve the competitive state-of-art result.