An official website of the United States government
Human-Robot Collaboration (HRC), which envisions a workspace in which human and robot can dynamically collaborate, has been identified as a key element in smart manufacturing. Human action recognition plays a key role in the realization of HRC as it helps identify current human action and provides the basis for future action prediction and robot planning. Despite recent development of Deep Learning (DL) that has demonstrated great potential in advancing human action recognition, one of the key issues remains as how to effectively leverage the temporal information of human motion to improve the performance of action recognition. Furthermore, large volume of training data is often difficult to obtain due to manufacturing constraints, which poses challenge for the optimization of DL models. This paper presents an integrated method based on optical flow and convolutional neural network (CNN)-based transfer learning to tackle these two issues. First, optical flow images, which encode the temporal information of human motion, are extracted and serve as the input to a two-stream CNN structure for simultaneous parsing of spatial-temporal information of human motion. Then, transfer learning is investigated to transfer the feature extraction capability of a pretrained CNN to manufacturing scenarios. Evaluation using engine block assembly confirmed the effectiveness of the developed method.
more »
« less
Representation Flow for Action Recognition
In this paper, we propose a convolutional layer inspired by optical flow algorithms to learn motion representations. Our representation flow layer is a fully-differentiable layer designed to capture the `flow' of any representation channel within a convolutional neural network for action recognition. Its parameters for iterative flow optimization are learned in an end-to-end fashion together with the other CNN model parameters, maximizing the action recognition performance. Furthermore, we newly introduce the concept of learning `flow of flow' representations by stacking multiple representation flow layers. We conducted extensive experimental evaluations, confirming its advantages over previous recognition models using traditional optical flows in both computational speed and performance. The code is publicly available.
more »
« less
- PAR ID:
- 10107545
- Date Published:
- Journal Name:
- Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition
- ISSN:
- 1063-6919
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Despite the advances in Human Activity Recognition, the ability to exploit the dynamics of human body motion in videos has yet to be achieved. In numerous recent works, re- searchers have used appearance and motion as independent inputs to infer the action that is taking place in a specific video. In this paper, we highlight that while using a novel representation of human body motion, we can benefit from appearance and motion simultaneously. As a result, bet- ter performance of action recognition can be achieved. We start with a pose estimator to extract the location and heat- map of body joints in each frame. We use a dynamic encoder to generate a fixed size representation from these body joint heat-maps. Our experimental results show that training a convolutional neural network with the dynamic motion representation outperforms state-of-the-art action recognition models. By modeling distinguishable activities as distinct dynamical systems and with the help of two stream net- works, we obtain the best performance on HMDB, JHMDB, UCF-101, and AVA datasets.more » « less
-
Spatiotemporal graph convolutional networks (STGCNs) have emerged as a desirable model for skeleton -based human action recognition. Despite achieving state-of-the-art performance, there is a limited understanding of the representations learned by these models, which hinders their application in critical and real-world settings. While layerwise analysis of CNN models has been studied in the literature, to the best of our knowledge, there exists no study on the layerwise explainability of the embeddings learned on spatiotemporal data using STGCNs. In this paper, we first propose to use a local Dataset Graph (DS-Graph) obtained from the feature representation of input data at each layer to develop an understanding of the layer-wise embedding geometry of the STGCN. To do so, we develop a window-based dynamic time warping (DTW) method to compute the distance between data sequences with varying temporal lengths. To validate our findings, we have developed a layer-specific Spatiotemporal Graph Gradient-weighted Class Activation Mapping (L-STG-GradCAM) technique tailored for spatiotemporal data. This approach enables us to visually analyze and interpret each layer within the STGCN network. We characterize the functions learned by each layer of the STGCN using the label smoothness of the representation and visualize them using our L-STG-GradCAM approach. Our proposed method is generic and can yield valuable insights for STGCN architectures in different applications. However, this paper focuses on the human activity recognition task as a representative application. Our experiments show that STGCN models learn representations that capture general human motion in their initial layers while discriminating different actions only in later layers. This justifies experimental observations showing that fine-tuning deeper layers works well for transfer between related tasks. We provide experimental evidence for different human activity datasets and advanced spatiotemporal graph networks to validate that the proposed method is general enough to analyze any STGCN model and can be useful for drawing insight into networks in various scenarios. We also show that noise at the input has a limited effect on label smoothness, which can help justify the robustness of STGCNs to noise.more » « less
-
3D object recognition accuracy can be improved by learning the multi-scale spatial features from 3D spatial geometric representations of objects such as point clouds, 3D models, surfaces, and RGB-D data. Current deep learning approaches learn such features either using structured data representations (voxel grids and octrees) or from unstructured representations (graphs and point clouds). Learning features from such structured representations is limited by the restriction on resolution and tree depth while unstructured representations creates a challenge due to non-uniformity among data samples. In this paper, we propose an end-to-end multi-level learning approach on a multi-level voxel grid to overcome these drawbacks. To demonstrate the utility of the proposed multi-level learning, we use a multi-level voxel representation of 3D objects to perform object recognition. The multi-level voxel representation consists of a coarse voxel grid that contains volumetric information of the 3D object. In addition, each voxel in the coarse grid that contains a portion of the object boundary is subdivided into multiple fine-level voxel grids. The performance of our multi-level learning algorithm for object recognition is comparable to dense voxel representations while using significantly lower memory.more » « less
-
Human-Robot Collaboration (HRC), which enables a workspace where human and robot can dynamically and safely collaborate for improved operational efficiency, has been identified as a key element in smart manufacturing. Human action recognition plays a key role in the realization ofHRC, as it helps identify current human action and provides the basis for future action prediction and robot planning. While Deep Learning (DL) has demonstrated great potential in advancing human action recognition, effectively leveraging the temporal information of human motions to improve the accuracy and robustness of action recognition has remained as a challenge. Furthermore, it is often difficult to obtain a large volume of data for DL network training and optimization, due to operational constraints in a realistic manufacturing setting. This paper presents an integrated method to address these two challenges, based on the optical flow and convolutional neural network (CNN)based transfer learning. Specifically, optical flow images, which encode the temporal information of human motion, are extracted and serve as the input to a two-stream CNN structure for simultaneous parsing of spatial-temporal information of human motion. Subsequently, transfer learning is investigated to transfer the feature extraction capability of a pre-trained CNN to manufacturing scenarios. Evaluation using engine block assembly confirmed the effectiveness of the developed method.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
