Scene recognition: A comprehensive survey

• Published in: Pattern recognition Vol. 102; p. 107205
• Main Authors: Xie, Lin, Lee, Feifei, Liu, Li, Kotani, Koji, Chen, Qiu
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01-06-2020
• Subjects: Convolutional neural networks; Deep learning; Discriminative region detection; Patch feature encoding; Scene recognition; Spatial layout pattern learning; Deep learning; Spatial layout pattern learning; Patch feature encoding; Discriminative region detection; Scene recognition; Convolutional neural networks
• ISSN: 0031-3203; 1873-5142
• DOI: 10.1016/j.patcog.2020.107205

•A comprehensive survey on scene recognition is presented.•Existing scene recognition algorithms are reviewed in the light of feature transformation.•The relations between various scene recognition algorithms are explored.•Current benchmarks of different methods are presented and analyzed for comparison.•Potential problems and future directions are identified.
With the success of deep learning in the field of computer vision, object recognition has made important breakthroughs, and its recognition accuracy has been drastically improved. However, the performance of scene recognition is still not sufficient to some extent because of complex configurations. Over the past several years, scene recognition algorithms have undergone important evolution as a result of the development of machine learning and Deep Convolutional Neural Networks (DCNN). This paper reviews many of the most popular and effective approaches to scene recognition, which is expected to create benefits for future research and practical applications. We seek to establish relationships among different algorithms and determine the critical components that lead to remarkable performance. Through the analysis of some representative schemes, motivation and insights are identified, which will help to facilitate the design of better recognition architectures. In addition, current available scene datasets and benchmarks are presented for evaluation and comparison. Finally, potential problems and promising directions are highlighted.