Video event recognition method based on deep residual long-short term memory network
A long-short-term memory and video event technology, applied in character and pattern recognition, biological neural network models, computer components, etc., can solve problems such as small distance between event classes, gradient disappearance, camera viewing angle changes, etc., to achieve good generalization The effects of ability and discrimination, shortening the intra-class distance, and improving discrimination
A long-short-term memory and video event technology, applied in character and pattern recognition, biological neural network models, computer components, etc., can solve problems such as small distance between event classes, gradient disappearance, camera viewing angle changes, etc., to achieve good generalization The effects of ability and discrimination, shortening the intra-class distance, and improving discrimination
CN108764009AInactive Publication Date: 2018-11-06SUZHOU UNIV +2
Image
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment approach
[0025] Shown in conjunction with accompanying drawing is the embodiment of a kind of video event recognition method based on depth residual long short-term memory network of the present invention, comprises the following steps:
[0026] Step 1) Design of spatio-temporal feature data connection unit: the spatio-temporal feature data is synchronously analyzed by LSTM to form a spatio-temporal feature data link unit DLSTM;
[0027] Such as figure 1 As shown, the specific steps include:
[0028] (1) Receive data: First, two LSTM units are used, which are respectively denoted as SLSTM and TLSTM, and SLSTM receives the feature h from the spatial CNN network SL , the TLSTM receives the feature h from the temporal CNN network TL ;
[0029] (2) Activation function conversion: Before receiving input, the LSTM unit needs to use a nonlinear activation function to process the input data, using the ReLU activation function, SLSTM and TLSTM are transformed by the ReLU activation function ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a video event recognition method based on a deep residual long-short term memory network, which comprises 1) the design of spatial-temporal feature data connection layer, thatis, spatial-temporal feature data is synchronously parsed through a long-short term memory (LSTM) unit and then forms a spatial-temporal feature data connection unit DLSTM (double-LSTM), and the consistency of spatial and temporal information is highlighted; (2) the design of a DU-DLSTM (dual unidirectional DLSTM) structure which expands the width of the network and increases the feature selectionrange; (3) the design of an RDU-DLSTM (residual dual unidirectional DLSTM) module which solves a deeper problem of network gradient disappearance; and 4) the design of a 2C-softmax objective functionwhich reduces the distance within classes while expanding the distance between the classes. The video event recognition method has the advantages that the problem of gradient disappearance is solvedthrough constructing the deep residual network framework, and the video event recognition accuracy is improved by using the consistency fusion of temporal network and spatial network features at the same time.
Description
technical field [0001] The invention relates to a video event recognition technology, in particular to a video event recognition method based on a deep residual long-short-term memory network. Background technique [0002] Video event recognition refers to the recognition of spatio-temporal visual patterns of events from videos. With the wide application of video surveillance in real life, surveillance video event recognition has received extensive attention and a series of research results have been achieved. However, event recognition of surveillance video still faces great challenges and difficulties, such as surveillance in natural scenes. Factors such as complex video background, severe object occlusion in the event area, and changes in camera viewing angles lead to small inter-class distances and large intra-class distances. [0003] In the existing technology, in order to solve the problem of difficult event recognition in surveillance video, the traditional solution...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
06 Nov 2018
Publication
CN108764009A
- IPC
- G06K9/00
- CPC
- G06N3/049; G06V20/44; G06V20/41; G06V20/46; G06N3/045
- Inventors
- 龚声蓉; 李永刚