Coarse-to-fine object detection in unmanned aerial vehicle imagery using lightweight convolutional neural network and deep motion saliency.
Jing ZhangXi LiangMeng WangLiheng YangLi ZhuoPublished in: Neurocomputing (2020)
Keyphrases
- lightweight
- coarse to fine
- object detection
- convolutional neural network
- face detection
- unmanned aerial vehicles
- optical flow estimation
- computer vision
- feature correspondences
- optical flow algorithm
- image sequences
- hierarchical segmentation
- object categories
- motion estimation
- multi class
- object class
- object recognition
- object segmentation
- optical flow
- camera motion
- motion model
- multiscale
- motion field
- multiresolution
- moving objects
- visual attention
- background subtraction
- path planning
- neural network
- rfid tags
- pattern recognition
- image pyramid
- motion planning
- image segmentation
- high resolution