Surveillance system with activity recognition
AssigneeNEC Corporation
InventorsKihyuk Sohn, Manmohan Chandraker, Xiang Yu
Life of this patent
Estimating the term…
Abstract
A computer-implemented method, system, and computer program product are provided for activity recognition in a surveillance system. The method includes receiving a plurality of unlabeled videos from one or more cameras. The method also includes classifying an activity in each of the plurality of unlabeled videos. The method additionally includes controlling an operation of a processor-based machine to react in accordance with the activity.
Claims17
A surveillance system utilizing activity recognition, the surveillance system comprising:
- one or more cameras;
- a processor and memory coupled to the processor forming a processing system, the processing system programmed to:
- receive the plurality of unlabeled videos from the one or more cameras;
- classify an activity in each of the plurality of unlabeled videos;
- and
- control an operation of a processor-based machine to react in accordance with the activity,
- wherein the processing system is further programmed to utilize a domain adversarial training system to classify the activity, and wherein the domain adversarial training system employs a frame-wise discriminator to learn differences between classified videos and the unlabeled videos at the frame level and to backpropagate the differences into a feature extraction CNN and a feature aggregation system.
A computer program product for a surveillance system with activity recognition, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method comprising:
- receiving a plurality of unlabeled videos from one or more cameras;
- classifying an activity in each of the plurality of unlabeled videos;
- and
- controlling an operation of a processor-based machine to react in accordance with the activity,
- wherein the computer is further programmed to utilize a domain adversarial training system to classify the activity, and wherein the domain adversarial training system employs a frame-wise discriminator to learn differences between classified videos and the unlabeled videos at the frame level and to backpropagate the differences into a feature extraction CNN and a feature aggregation system.
A computer-implemented method for activity recognition in a surveillance system, the method comprising:
- receiving a plurality of unlabeled videos from one or more cameras;
- classifying an activity in each of the plurality of unlabeled videos;
- and
- controlling an operation of a processor-based machine to react in accordance with the activity,
- wherein classifying determines an average of the frame features, determines a weighted average of the frame features responsive to a weighting factor, and employs both a short-term memory neural network and a gated recurrent unit network.
Dependencies are inferred from the claim text.