Deep learning-based small object detection: A survey

Small object detection (SOD) is significant for many real-world applications, including criminal investigation, autonomous driving and remote sensing images. SOD has been one of the most challenging tasks in computer vision due to its low resolution and noise representation. With the development of deep learning, it has been introduced to boost the performance of SOD. In this paper, focusing on the difficulties of SOD, we analyze the deep learning-based SOD research papers from four perspectives, including boosting the resolution of input features, scale-aware training, incorporating contextual information and data augmentation. We also review the literature on crucial SOD tasks, including small face detection, small pedestrian detection and aerial image object detection. In addition, we conduct a thorough performance evaluation of generic SOD algorithms and methods for crucial SOD tasks on four well-known small object datasets. Our experimental results show that network configuring to boost the resolution of input features can enable significant performance gains on WIDER FACE and Tiny Person. Finally, several potential directions for future research in the area of SOD are provided.

Automated summary

Small object detection is important for various real-world applications, and it remains a challenging task in computer vision due to its low resolution and noise representation. This paper focuses on the difficulties of small object detection and analyzes deep learning-based research papers from multiple perspectives. The authors also review literature on crucial tasks such as small face detection and aerial image object detection. Experimental results show that network configuration to enhance the resolution of input features can significantly improve performance. Several potential future research directions in the field of small object detection are also provided.