An Intelligent Video Surveillance System for Anomaly Detection in Home Environment Using a Depth Camera
01 Jan 2019-pp 473-481
TL;DR: A simple yet efficient technique to detect fall with the help of inexpensive depth camera was presented and it was observed that SGD classifier gives better fall detection accuracy than the SVM classifier in both training and testing phase for SDU fall dataset.
Abstract: In recent years, the research on the anomaly detection has been rapidly increasing. The researchers were worked on different anomalies in videos. This work focuses on fall as an anomaly as it is an emerging research topic with application in elderly safety areas including home environment. The older population staying alone at home is prone to various accidental events including falls which may lead to multiple harmful consequences even death. Thus, it is imperative to develop a robust solution to avoid this problem. This can be done with the help of video surveillance along with computer vision. In this paper, a simple yet efficient technique to detect fall with the help of inexpensive depth camera was presented. Frame differencing method was applied for background subtraction. Various features including orientation angle, aspect ratio, silhouette features, and motion history image (MHI) were extracted for fall characterization. The training and testing were successfully implemented using SVM and SGD classifiers. It was observed that SGD classifier gives better fall detection accuracy than the SVM classifier in both training and testing phase for SDU fall dataset.
Citations
More filters
Posted Content•
TL;DR: A heterogeneous system that estimates the degree of an anomaly in unmanned surveillance drone by inspecting IMU (Inertial Measurement Unit) sensor data and real-time image in an unsupervised approach is demonstrated.
Abstract: Anomaly detection (AD) in a surveillance scenario is an emerging and challenging field of research. For autonomous vehicles like drones or cars, it is immensely important to distinguish between normal and abnormal states in real-time. Additionally, we also need to detect any device malfunction. But the nature and degree of abnormality may vary depending upon the actual environment and adversary. As a result, it is impractical to model all cases a-priori and use supervised methods to classify. Also, an autonomous vehicle provides various data types like images and other analog or digital sensor data, all of which can be useful in anomaly detection if leveraged fruitfully. To that effect, in this paper, a heterogeneous system is proposed which estimates the degree of abnormality of an unmanned surveillance drone, analyzing real-time image and IMU (Inertial Measurement Unit) sensor data in an unsupervised manner. Here, we have demonstrated a Convolutional Neural Network (CNN) architecture, named AngleNet to estimate the angle between a normal image and another image under consideration, which provides us with a measure of anomaly of the device. Moreover, the IMU data are used in autoencoder to predict abnormality. Finally, the results from these two algorithms are ensembled to estimate the final degree of abnormality. The proposed method performs satisfactorily on the IEEE SP Cup-2020 dataset with an accuracy of 97.3%. Additionally, we have also tested this approach on an in-house dataset to validate its robustness.
6 citations
01 Jan 2022
TL;DR: The smart jacket for visually impaired people or say visually impaired system (VIS) as discussed by the authors supports this process by providing key facilities a short-range system for detecting obstacles, a short range system for identifying obstacles, signboard recognition system, and the shortest path guidance system for source to destination.
Abstract: Blindness is one of those world's most feared afflictions. Blind people have trouble getting to the desired destination. The smart jacket for visually impaired people or say visually impaired system (VIS) supports this process by providing key facilities a short-range system for detecting obstacles, a short-range system for identifying obstacles, a signboard recognition system, and the shortest path guidance system for source to destination. Obstacle detection, distress calling, global location tracking, voice command functionality, and shortest route guidance are all features of this system in real time. The aim is to build a program that will direct visually disabled people arrive at the destination they want and help them understand the natural world around them. The blind or visually impaired rely primarily on other senses such as sound, touch, and smell to perceive their surroundings. We find it very daunting to go out alone, not to mention toilets, subway stations, restaurants, and so on. The visually impaired program seeks to make blind people fully exposed to their surroundings.
2 citations
References
More filters
01 Dec 2015
TL;DR: An improved depth-based fall detection system that uses shape based fall characterization and a Support Vector Machines (SVM) classifier to classify falls from other daily actions and is 2% more accurate than the compared approach.
Abstract: FV can be considered as a generalization of the BoW. In other words, BoW is a particular case of the FV. The additional gradients improve the FV's performance greatly.Smaller codebooks can be used to construct the FV, which yields lower computational cost.FV performs well even with simple linear classifiers. Elderly people, who are living alone, are at great risk if a fall event occurred. Thus, automatic fall detection systems are in demand. Some of the early automatic fall detection systems such as wearable devices has a high cost and may cause inconvenience to the daily lives of the elderly people. In this paper, an improved depth-based fall detection system is presented. Our approach uses shape based fall characterization and a Support Vector Machines (SVM) classifier to classify falls from other daily actions. Shape based fall characterization is carried out with Curvature Scale Space (CSS) features and Fisher Vector (FV) encoding. FV encoding is used because it has several advantages against the Bag-of-Words (BoW) model. FV representation is robust and performs well even with simple linear classifiers. Extensive experiments on SDUFall dataset, which contains five daily activities and intentional falls from 20 subjects, show that encoding CSS features with FV encoding and a SVM classifier can achieve an up to 88.83% fall detection accuracy with a single depth camera. This classification rate is 2% more accurate than the compared approach. Moreover, an overall 64.67% accuracy is obtained for 6-class action recognition, which is about 10% more accurate than the compared approach.
69 citations
TL;DR: A fast and robust shape sequence descriptor, namely the Silhouette Orientation Volume (SOV), is used to represent actions and classify falls and a perfect silhouette-based action recognition rate of 100% is achieved on the Weizmann action dataset.
Abstract: A novel method to detect human falls in depth videos is presented in this paper. A fast and robust shape sequence descriptor, namely the Silhouette Orientation Volume (SOV), is used to represent actions and classify falls. The SOV descriptor provides high classification accuracy even with a combination of simple associated models, such as Bag-of-Words and the Naive Bayes classifier. Experiments on the public SDU-Fall dataset show that this new approach achieves up to 91.89% fall detection accuracy with a single-view depth camera. The classification rate is about 5% higher than the results reported in the literature. An overall accuracy of 89.63% was obtained for the six-class action recognition, which is about 25% higher than the state of the art. Moreover, a perfect silhouette-based action recognition rate of 100% is achieved on the Weizmann action dataset.
54 citations
TL;DR: The backward fall was the most difficult to avoid among the three kinds of fall events due to the toughest combination of shortest lead time and smallest angle of postural stability which made it difficult for the self-protective control mechanism to adjust the body in time to avoid falling down.
Abstract: The unintentional injuries due to falls in elderly people give rise to a multitude of health and economic problems due to the growing aging population. The use of early pre-impact fall alarm and self-protective control could greatly reduce fall injuries. This paper aimed to explore and implement a pre-impact fall recognition/alarm method for free-direction fall activities based on understanding of the pre-impact lead time of falls and the angle of body postural stability using an inertial body sensor network. Eight healthy Asian adult subjects were arranged to perform three kinds of daily living activities and three kinds of fall activities. Nine MTx sensor modules were used to measure the body segmental kinematic characteristics of each subject for pre-impact fall recognition/alarm. Our analysis of the kinematic features of human body segments showed that the chest was the optimal sensor placement for an early pre-impact recognition/alarm (i.e., prediction/alarm of a fall event before it happens) and post-fall detection (i.e., detection of a fall event after it already happened). Furthermore, by comparative analysis of threshold levels for acceleration and angular rate, two acceleration thresholds were determined for early pre-impact alarm (7 m/s/s) and post-fall detection (20 m/s/s) under experimental conditions. The critical angles of postural stability of torso segment in three kinds of fall activities (forward, sideway and backward fall) were determined as 23.9 ± 3.3, 49.9 ± 4.1 and 9.9 ± 2.5 degrees, respectively, and the relative average pre-impact lead times were 329 ± 21, 265 ± 35 and 257 ± 36 ms. The results implied that among the three fall activities the sideway fall was associated with the largest postural stability angle and the forward fall was associated with the longest time to adjust body angle to avoid the fall; the backward fall was the most difficult to avoid among the three kinds of fall events due to the toughest combination of shortest lead time and smallest angle of postural stability which made it difficult for the self-protective control mechanism to adjust the body in time to avoid falling down.
54 citations
TL;DR: Using wireless ambient sensors (dual-technology (microwave/infrared) motion detectors and pressure mats) to track the movement of multiple persons and to unobtrusively detect falls when they occur is investigated, therefore reducing the rate of occurrence of “long lie” scenarios.
Abstract: One serious issue related to falls among the elderly living at home or in a residential care facility is the “long lie” scenario, which involves being unable to get up from the floor after a fall for 60 min or more. This research uses a simulated environment to investigate the potential effectiveness of using wireless ambient sensors (dual-technology (microwave/infrared) motion detectors and pressure mats) to track the movement of multiple persons and to unobtrusively detect falls when they occur, therefore reducing the rate of occurrence of “long lie” scenarios. A path-finding algorithm (A*) is used to simulate the movement of one or more persons through the residential area. For analysis, the sensor network is represented as an undirected graph, where nodes in the graph represent sensors, and edges between nodes in the graph imply that these sensors share an overlapping physical region in their area of sensitivity. A second undirected graph is used to represent the physical adjacency of the sensors (even where they do not overlap in their monitored regions). These graphical representations enable the tracking of multiple subjects/groups within the environment, by analyzing the sensor activation and adjacency profiles, hence allowing individuals/groups to be isolated when multiple persons are present, and subsequently monitoring falls events. A falls algorithm, based on a heuristic decision tree classifier model, was tested on 15 scenarios, each including one or more persons; three scenarios of activity of daily living, and 12 different types of falls (four types of fall, each with three postfall scenarios). The sensitivity, specificity, and accuracy of the falls algorithm are 100.00%, 77.14%, and 89.33%, respectively.
36 citations
01 Jan 2009
TL;DR: This paper proposes a new approach to deal with unintentional falls, which is one of the greatest risks for seniors living alone, based on a combination of motion gradients and human shape features variation.
Abstract: Unintentional falls are common causes of serious injuries and health threats to patients as well as senior citizens living alone. Advanced computer vision algorithms and low cost cameras can be used for assessment of health hazards such as falls. In this paper, we propose a new approach to deal with this particular problem i.e. to detect unintentional falls, which are one of the greatest risks for seniors living alone. Our proposed approach is based on a combination of motion gradients and human shape features variation. Our proposed system provides promising results on video sequences of simulated falls.
23 citations