计算机科学
人工智能
目标检测
计算机视觉
对象(语法)
特征(语言学)
模式识别(心理学)
图像分辨率
分辨率(逻辑)
采样(信号处理)
语言学
滤波器(信号处理)
哲学
作者
Zixuan Yang,Xiujuan Chai,Ruiping Wang,Wei-Jun Guo,Weixuan Wang,Li Jin Pu,Xilin Chen
出处
期刊:International Conference on Image Processing
日期:2019-09-01
被引量:4
标识
DOI:10.1109/icip.2019.8802612
摘要
When applying common object detection algorithms to detect small objects on high-resolution images, the down-sampling operation of the input images is inevitable due to the limitation of GPU memory. Accordingly, the details for characterizing small objects are lost. To resolve this contradiction, a small object detection method in a coarse-to-fine manner is presented. Specifically, some rough regions of interest (ROI) are firstly computed from low-resolution images. The prior knowledge of the positions of objects is used to guide the generation of ROIs. Then the features of small ROIs are recomputed from high-resolution images, and the features of large ROIs are obtained from the feature maps used to generate ROIs. The proposed method is validated on two datasets. One is a plant phenotyping dataset and the other is a public traffic sign dataset. Experimental results convincingly show the effectiveness of the proposed method.
科研通智能强力驱动
Strongly Powered by AbleSci AI