Food safety is affected by the conditions and practices during different manufacturing steps to prevent contamination and food-borne illnesses. In this paper, we focus on detecting hand-hygiene actions in Egocentric videos. We create a two-stage system to localize and recognize all the hand-hygiene actions in each untrimmed video. In the first stage, we apply a low-cost hand mask and motion histogram features to localize the temporal regions of hand-hygiene actions. In the second stage, we use the two-stream network model combined with a search algorithm to recognize all types of hand-hygiene actions that happen in the untrimmed video. The system achieves a detection accuracy close to 80% on our dataset with 100 participants.

A majority of foodborne illnesses result from inappropriate food handling practices. One proven practice to reduce pathogens is to perform effective hand-hygiene before all stages of food handling. In this paper, we design a multi-camera system that uses video analytics to recognize hand-hygiene actions, with the goal of improving hand-hygiene effectiveness. Our proposed two-stage system processes untrimmed video from both egocentric and third-person cameras. In the first stage, a low-cost coarse classifier efficiently localizes the hand-hygiene period; in the second stage, more complex refinement classifiers recognize seven specific actions within the hand-hygiene period. We demonstrate that our two-stage system has significantly lower computational requirements without a loss of recognition accuracy. Specifically, the computationally complex refinement classifiers process less than 68% of the untrimmed videos, and we anticipate further computational gains in videos that contain a larger fraction of non-hygiene actions. Our results demonstrate that a carefully designed video action recognition system can play an important role in improving hand hygiene for food safety.

Hand-hygiene is a critical component for safe food handling. In this paper, we apply an iterative engineering process to design a hand-hygiene action detection system to improve food-handling safety. We demonstrate the feasibility of a baseline RGB-only convolutional neural network (CNN) in the restricted case of a single scenario; however, since this baseline system performs poorly across scenarios, we also demonstrate the application of two methods to explore potential reasons for its poor performance. This leads to the development of our hierarchical system that incorporates a variety of modalities (RGB, optical flow, hand masks, and human skeleton joints) for recognizing subsets of hand-hygiene actions. Using hand-washing video recorded from several locations in a commercial kitchen, we demonstrate the effectiveness of our system for detecting hand hygiene actions in untrimmed videos. In addition, we discuss recommendations for designing a computer vision system for a real application.

Executing video analytics tasks using a large camera network is a challenging problem in the field of video processing. Video compression is a necessary step to reduce video data size before transmission. However, the performance of video analytics tasks generally degrade as video quality drops. This paper considers how to find the optimal point between video compression and performance for the video analytics task of activity recognition. We propose a system that predicts the success or failure of a video analytics task under different compression parameters without executing the task. The system is designed to automatically select the best compression rate for each video to maintain an acceptable detection accuracy. Our experiments indicate that such a system has the potential to improve overall performance across a variety of different activity sets selected from the UCF101 dataset [1].