Fall Detection for Shipboard Seafarers Based on Optimized BlazePose and LSTM

Abstract

Aiming to avoid personal injury caused by the failure of timely medical assistance following a fall by seafarer members working on ships, research on the detection of seafarer’s falls and timely warnings to safety officers can reduce the loss and severe consequences of falls to seafarers. To improve the detection accuracy and real-time performance of the seafarer fall detection algorithm, a seafarer fall detection algorithm based on BlazePose–LSTM is proposed. This algorithm can automatically extract the human body key point information from the video image obtained by the vision sensor, analyze its internal data correlation characteristics, and realize the process from RGB camera image processing to seafarer fall detection. This fall detection algorithm extracts the human body key point information through the optimized BlazePose human body key point information extraction network. In this section, a new method for human bounding-box acquisition is proposed. In this study, a head detector based on the Vitruvian theory was used to replace the pre-trained SSD body detector in the BlazePose preheating module. Simultaneously, an offset vector is proposed to update the bounding box obtained. This method can reduce the frequency of repeated use of the head detection module. The algorithm then uses the long short-term memory neural network to detect seafarer falls. After extracting fall and related behavior data from the URFall public data set and FDD public data set to enrich the self-made data set, the experimental results show that the algorithm can achieve 100% accuracy and 98.5% specificity for the seafarer’s falling behavior, indicating that the algorithm has reasonable practicability and strong generalization ability. The detection frame rate can reach 29 fps on a CPU, which can meet the effect of real-time detection. The proposed method can be deployed on common vision sensors.

Towards Automating Personal Exercise Assessment and Guidance with Affordable Mobile Technology

“…Despite the excellent performance, we avoided the use of a sensor system due to cost and simplicity considerations. Numerous research studies have employed ML models using BlazePose keypoint data to predict falls in real-time scenarios [29,30]. To our knowledge, the work of Arrowsmith et al is the only other approach utilizing BlazePose for classifying physiotherapy exercises [31].…”

A novel lightweight deep learning fall detection system based on Global-Local attention and channel feature augmentation

“…Notably, these images encompass individuals of all age groups, including children and elderly individuals. In comparison to previously reported fall detection systems 49,50 , this dataset represented one of the most extensive collections of fall images that have been utilized for classifier training to our knowledge.…”

Visual Perception and Multimodal Control: A Novel Approach to Designing an Intelligent Badminton Serving Device

“…The detector-tracker is composed of a body posture detector and a posture tracker; when there is an image input, the tracker predicts keypoint coordinates, and when the tracker indicates that there is no human present, re-run the detector network on the next frame. This method effectively improves the accuracy of the recognition of human body poses, and it is currently one of the most widely used methods [19,20]. Although this method can accurately identify information about the human body's pose, the recognition process is run repeatedly for the same posture, resulting in a large computational burden and making it difficult to deploy on embedded computers.…”