The unprecedented success of deep convolutional neural networks (CNN) on the task of video-based human action recognition assumes the availability of good resolution videos and resources to develop and deploy complex models. Unfortunately, certain budgetary and environmental constraints on the camera system and the recognition model may not be able to accommodate these assumptions and require reducing their complexity. To alleviate these issues, we introduce a deep sensing solution to directly recognize human actions from coded exposure images. Our deep sensing solution consists of a binary CNN-based encoder network that emulates the capturing of a coded exposure image of a dynamic scene using a coded exposure camera, followed by a 2D CNN for recognizing human action in the captured coded exposure image. Furthermore, we propose a novel knowledge distillation framework to jointly train the encoder and the action recognition model and show that the proposed training approach improves the action recognition accuracy by an absolute margin of 6.2%, 2.9%, and 7.9% on Something$^{2}$-v2, Kinetics-400, and UCF-101 datasets, respectively, in comparison to our previous approach. Finally, we built a prototype coded exposure camera using LCoS to validate the feasibility of our deep sensing solution. Our evaluation of the prototype camera show results that are consistent with the simulation results.

We propose a method for compressively acquiring a dynamic light field (a 5-D volume) through a single-shot coded image (a 2-D measurement). We designed an imaging model that synchronously applies aperture coding and pixel-wise exposure coding within a single exposure time. This coding scheme enables us to effectively embed the original information into a single observed image. The observed image is then fed to a convolutional neural network (CNN) for light-field reconstruction, which is jointly trained with the camera-side coding patterns. We also developed a hardware prototype to capture a real 3-D scene moving over time. We succeeded in acquiring a dynamic light field with 5x5 viewpoints over 4 temporal sub-frames (100 views in total)from a single observed image. Repeating capture and reconstruction processes over time, we can acquire a dynamic light field at 4x the frame rate of the camera. To our knowledge, our method is the first to achieve a finer temporal resolution than the camera itself in compressive light-field acquisition. Our software is available from our project webpage.11https://www.fujii.nuee.nagoya-u.ac.jp/Research/CompCam2

Cameras are prevalent in society at the present time, for example, surveillance cameras, and smartphones equipped with cameras and smart speakers. There is an increasing demand to analyze human actions from these cameras to detect unusual behavior or within a man-machine interface for Internet of Things (IoT) devices. For a camera, there is a trade-off between spatial resolution and frame rate. A feasible approach to overcome this trade-off is compressive video sensing. Compressive video sensing uses random coded exposure and reconstructs higher than read out of sensor frame rate video from a single coded image. It is possible to recognize an action in a scene from a single coded image because the image contains multiple temporal information for reconstructing a video. In this paper, we propose reconstruction-free action recognition from a single coded exposure image. We also proposed deep sensing framework which models camera sensing and classification models into convolutional neural network (CNN) and jointly optimize the coded exposure and classification model simultaneously. We demonstrated that the proposed method can recognize human actions from only a single coded image. We also compared it with competitive inputs, such as low-resolution video with a high frame rate and high-resolution video with a single frame in simulation and real experiments.