SegCodeNet: Color-Coded Segmentation Masks for Activity Detection from Wearable Cameras

Activity detection from first-person videos (FPV) captured using a wearable camera is an active research field with potential applications in many sectors, including healthcare, law enforcement, and rehabilitation. State-of-the-art methods use optical flow-based hybrid techniques that rely on features derived from the motion of objects from consecutive frames. In this work, we developed a two-stream network, the SegCodeNet, that uses a network branch containing video-streams with color-coded semantic segmentation masks of relevant objects in addition to the original RGB video-stream. We also include a stream-wise attention gating that prioritizes between the two streams and a frame-wise attention module that prioritizes the video frames that contain relevant features. Experiments are conducted on an FPV dataset containing 18 activity classes in office environments. In comparison to a single-stream network, the proposed two-stream method achieves an absolute improvement of 14.366% and 10.324% for averaged F1 score and accuracy, respectively, when average results are compared for three different frame sizes 224×224, 112×112, and 64×64. The proposed method provides significant performance gains for lower-resolution images with absolute improvements of 17% and 26% in F1 score for input dimensions of 112×112 and 64×64, respectively. The best performance is achieved for a frame size of 224×224 yielding an F1 score and accuracy of 90.176% and 90.799% which outperforms the state-of-the-art Inflated 3D ConvNet (I3D) citecarreira2017quo method by an absolute margin of 4.529% and 2.419%, respectively.