"We present a detailed design of dynamic
video segmentation network (DVSNet) for fastefficient
semantic video segmentation. DVSNet consists of two convolutional neural networks: a segmentation network and
a flow network. The former generates highly accurate se-
mantic segmentations, but is deeperslower. The latter
is much faster than the former, but its output requires further processing

"The contributions of this work are as follows:
1. A frame division technique to apply different segmentation
strategies to different frame regions for maximizing
the usage of video redundancycontinuity.
2. A DN for determining whether to assign an input frame
region to the segmentation network,adaptively adjusting
the update period of the key frames.
3. An adaptive key frame scheduling 

"The main applications focused in this project are visual recognition
applications for smart robot. W  focus on developing deep learning
techniques for video semantic segmentation. The techniques
developed in this project can be used not only for robotic industry but also for video surveillance industry."