A Depth-Based Fall Detection System Using a Kinect® Sensor

By Samuele Gasparrini, Enea Cippitelli, Susanna Spinsante, Ennio Gambi. 2014

209 citations recorded by the source corpus.

We propose an automatic, privacy-preserving, fall detection method for indoor environments, based on the usage of the Microsoft Kinect® depth sensor, in an “on-ceiling” configuration, and on the analysis of depth frames. All the elements captured in the depth scene are recognized by means of an Ad-Hoc segmentation algorithm, which analyzes the raw depth data directly provided by the sensor. The system extracts the elements, and implements a solution to classify all the blobs in the scene. Anthropometric relationships and features are exploited to recognize one or more human subjects among the blobs. Once a person is detected, he is followed by a tracking algorithm between different frames. The use of a reference depth frame, containing the set-up of the scene, allows one to extract a human subject, even when he/she is interacting with other objects, such as chairs or desks. In addition, the problem of blob fusion is taken into account and efficiently solved through an inter-frame processing algorithm. A fall is detected if the depth blob associated to a person is near to the floor. Experimental tests show the effectiveness of the proposed solution, even in complex scenarios.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Electrical and Electronic Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In Electrical and Electronic Engineering

Citations in the corpus

RGB-D datasets using microsoft kinect or similar sensors: a survey (2016, methodology): “The curves under the images are the accelerometer data at 50 Hz of devices attached to the knife, the mixing spoon, the small spoon, the peeler, the glass, the oil bottle, and the pepper dispenser mentioned datasets above, another 26 extra RGB-D datasets for different applications are also added int”
Evaluation of a skeleton-based method for human activity recognition on a large-scale RGB-D dataset (2016, methodology): “Tests have been executed considering C = 1 for the SVM, different levels of the temporal pyramid (L = [2, 3, 4]), and the same number of clusters for each action of the dataset, setting K = K1 = K2 = · · · = KM .”
Survey on Fall Detection and Fall Prevention Using Wearable and External Sensors (2014, methodology): “[26] developed a fall detection system using a depth camera (Microsoft Kinect).”
Time synchronization and data fusion for RGB-Depth cameras and inertial sensors in AAL applications (2015, background): “Nowadays, wearable and vision-based sensors are alternately used in AAL solutions, but their joint use can overcome the limitations of both the technologies.”
A survey of depth and inertial sensor fusion for human action recognition (2015, background): “The TST fall detection database 7 [27] is another multimodal database which focuses on fall detection.”
Skeleton-based Human Activity Recognition for Video Surveillance (2015, background): “The advantages of this technology, with respect to classical video-based ones, are [13]:  Being less sensitive to variations in light intensity and texture changes;  Providing 3D information by a single camera, while a stereoscopic system is necessary in the RGB domain to achieve the same goal;  ”
RGBD Datasets: Past, Present and Future (2016, background): “Other datasets contain labels appropriate for tracking: two semantic scene datasets [112, 62] have static objects labeled through video as the camera moves, while the 6-DOF object pose annotations in [45] could also be useful.”