Exploring Deep Learning-Based Architecture, Strategies, Applications and Current Trends in Generic Object Detection: A Comprehensive Review
| Autor: | Sara Ayub, Md. Sah Bin Haji Salam, Lubna Aziz, Usman Ullah Sheikh |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
convolutional neural networks (CNN)
General Computer Science Relation (database) neural network Computer science Object detection and recognition 02 engineering and technology Machine learning computer.software_genre 01 natural sciences Field (computer science) 0202 electrical engineering electronic engineering information engineering General Materials Science business.industry Deep learning 010401 analytical chemistry General Engineering deep learning 020206 networking & telecommunications Object (computer science) Object detection 0104 chemical sciences Variety (cybernetics) Benchmark (computing) lcsh:Electrical engineering. Electronics. Nuclear engineering Artificial intelligence business Focus (optics) lcsh:TK1-9971 computer |
| Zdroj: | IEEE Access, Vol 8, Pp 170461-170495 (2020) |
| ISSN: | 2169-3536 |
| DOI: | 10.1109/access.2020.3021508 |
| Popis: | Object detection is a fundamental but challenging issue in the field of generic image analysis; it plays an important role in a wide range of applications and has been receiving special attention in recent years. Although there are enomerous methods exist, an in-depth review of the literature concerning generic detection remains. This paper provides a comprehensive survey of recent advances in visual object detection with deep learning. Covering about 300 publications that we survey 1) region proposal-based object detection methods such as R-CNN, SPPnet, Fast R-CNN, Faster R-CNN, Mask RCN, RFCN, FPN, 2) classification/regression base object detection methods such as YOLO(v2 to v5), SSD, DSSD, RetinaNet, RefineDet, CornerNet, EfficientDet, M2Det 3) Some latest detectors such as, relation network for object detection, DCN v2, NAS FPN. Moreover, five publicly available benchmark datasets and their standard evaluation metrics are also discussed. We mainly focus on the application of deep learning architectures to five major applications, namely Object Detection in Surveillance, Military, Transportation, Medical, and Daily Life. In the survey, we cover a variety of factors affecting the detection performance in detail, such as i) a wide range of object categories and intra-class variations, ii) limited storage capacity and computational power. Finally, we finish the survey by identifying fifteen current trends and promising direction for future research. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|