Human action recognition in drone videos
A method is provided for drone-video-based action recognition. The method learns a transformation for each of target video clips taken from a set of target videos, responsive to original features extracted from the target video clips. The transformation corrects differences between a target drone domain corresponding to the target video clips and a source non-drone domain corresponding to source video clips taken from a set of source videos. The method adapts the target to the source domain by applying the transformation to the original features to obtain transformed features for the target video clips. The method converts the original and transformed features of same ones of the target video clips into a single classification feature for each of the target videos. The method classifies a human action in a new target video relative to the set of source videos using the single classification feature for each of the target videos.
1. A computer-implemented method for drone-video-based action recognition, comprising:
learning, by a hardware processor, a respective transformation for each of a plurality of target video clips taken from a set of target videos, responsive to original features extracted from the plurality of target video clips, the respective transformation for correcting differences between a target drone domain corresponding to the plurality of target video clips and a source non-drone domain corresponding to a plurality of source video clips taken from a set of source videos;
adapting, by the hardware processor, the target domain to the source domain by applying the respective transformation to the original features extracted from the plurality of target video clips to obtain transformed features for the plurality of target video clips;
converting, by the hardware processor, the original features and the transformed features of same ones of the plurality of target video clips into a single classification feature for each of the target videos in the set; and
classifying, by the hardware processor, a human action in a new target video relative to the set of source videos using the single classification feature for each of the target videos in the set.
2. The computer-implemented method of claim 1 , further comprising extracting the original features using a convolutional neural network.
3. The computer-implemented method of claim 1 , wherein said learning step learns the respective transformation that corrects for viewpoint differences between the source domain and the target domain.
4. The computer-implemented method of claim 1 , wherein said learning step learns the respective transformation that corrects for motion differences between the source domain and the target domain.
5. The computer-implemented method of claim 1 , wherein said converting step is performed on the original features and the transformed features using a dimension-wise maximum function.
6. The computer-implemented method of claim 1 , wherein said converting step is performed the original features and the transformed features using an averaging function.
7. The computer-implemented method of claim 1 , wherein the hardware processor uses a Support Vector Regressor to predict parameters of the respective transformation.
8. The computer-implemented method of claim 1 , further comprising capturing, by a drone, the target videos in the set.
9. The computer-implemented method of claim 1 , wherein said adapting step finetunes a neural network used said classifying step to align the target drone domain to the source non-drone domain.
10. A computer program product for unsupervised domain adaptation for video classification, 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:
learning, by a hardware processor, a respective transformation for each of a plurality of target video clips taken from a set of target videos, responsive to original features extracted from the plurality of target video clips, the respective transformation for correcting differences between a target drone domain corresponding to the plurality of target video clips and a source non-drone domain corresponding to a plurality of source video clips taken from a set of source videos;
adapting, by the hardware processor, the target domain to the source domain by applying the respective transformation to the original features extracted from the plurality of target video clips to obtain transformed features for the plurality of target video clips;
converting, by the hardware processor, the original features and the transformed features of same ones of the plurality of target video clips into a single classification feature for each of the target videos in the set; and
classifying, by the hardware processor, a human action in a new target video relative to the set of source videos using the single classification feature for each of the target videos in the set.
11. The computer-implemented method of claim 10 , wherein the method further comprises extracting the original features using a convolutional neural network.
12. The computer-implemented method of claim 10 , wherein said learning step learns the respective transformation that corrects for viewpoint differences between the source domain and the target domain.
13. The computer-implemented method of claim 10 , wherein said learning step learns the respective transformation that corrects for motion differences between the source domain and the target domain.
14. The computer-implemented method of claim 10 , wherein said converting step is performed on the original features and the transformed features using a dimension-wise maximum function.
15. The computer-implemented method of claim 10 , wherein said converting step is performed the original features and the transformed features using an averaging function.
16. The computer-implemented method of claim 10 , wherein the hardware processor uses a Support Vector Regressor to predict parameters of the respective transformation.
17. The computer-implemented method of claim 10 , wherein the method further comprises capturing, by a drone, the target videos in the set.
18. The computer-implemented method of claim 10 , wherein said adapting step finetunes a neural network used said classifying step to align the target drone domain to the source non-drone domain.
19. A computer processing system for drone-video-based action recognition, comprising:
a memory for storing program code; and
a hardware processor for running the program code to
learn a respective transformation for each of a plurality of target video clips taken from a set of target videos, responsive to original features extracted from the plurality of target video clips, the respective transformation for correcting differences between a target drone domain corresponding to the plurality of target video clips and a source non-drone domain corresponding to a plurality of source video clips taken from a set of source videos;
adapt the target domain to the source domain by applying the respective transformation to the original features extracted from the plurality of target video clips to obtain transformed features for the plurality of target video clips;
convert the original features and the transformed features of same ones of the plurality of target video clips into a single classification feature for each of the target videos in the set; and
classify a human action in a new target video relative to the set of source videos using the single classification feature for each of the target videos in the set.
20. The computer processing system of claim 19 , wherein the hardware processor uses a Support Vector Regressor to predict parameters of the respective transformation.