Detection of Human Falls on Furniture Using Scene Analysis Based on Deep Learning and Activity Characteristics

Min, Weidong; Cui, Hao; Hong, Rongjing; Li, Zhixun; Yao, Leiyue

doi:10.1109/access.2018.2795239

Cited by 83 publications

(36 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Springer [ 40 ] et al showed that the best angle for visual screen was 15°–30° below horizontal sight. Based on ergonomics [ 37 , 41 ], our method comprehensively extracts features that are strongly correlated with sitting posture health from human body joints, persons and scenes [ 42 ], as illustrated in Figure 5 .…”

Section: Our Proposed Methods Based On Scene Recognition and Semantmentioning

confidence: 99%

A Scene Recognition and Semantic Analysis Approach to Unhealthy Sitting Posture Detection during Screen-Reading

Min

Cui

Han

et al. 2018

Sensors

Self Cite

View full text Add to dashboard Cite

Behavior analysis through posture recognition is an essential research in robotic systems. Sitting with unhealthy sitting posture for a long time seriously harms human health and may even lead to lumbar disease, cervical disease and myopia. Automatic vision-based detection of unhealthy sitting posture, as an example of posture detection in robotic systems, has become a hot research topic. However, the existing methods only focus on extracting features of human themselves and lack understanding relevancies among objects in the scene, and henceforth fail to recognize some types of unhealthy sitting postures in complicated environments. To alleviate these problems, a scene recognition and semantic analysis approach to unhealthy sitting posture detection in screen-reading is proposed in this paper. The key skeletal points of human body are detected and tracked with a Microsoft Kinect sensor. Meanwhile, a deep learning method, Faster R-CNN, is used in the scene recognition of our method to accurately detect objects and extract relevant features. Then our method performs semantic analysis through Gaussian-Mixture behavioral clustering for scene understanding. The relevant features in the scene and the skeletal features extracted from human are fused into the semantic features to discriminate various types of sitting postures. Experimental results demonstrated that our method accurately and effectively detected various types of unhealthy sitting postures in screen-reading and avoided error detection in complicated environments. Compared with the existing methods, our proposed method detected more types of unhealthy sitting postures including those that the existing methods could not detect. Our method can be potentially applied and integrated as a medical assistance in robotic systems of health care and treatment.

show abstract

Section: Our Proposed Methods Based On Scene Recognition and Semantmentioning

confidence: 99%

A Scene Recognition and Semantic Analysis Approach to Unhealthy Sitting Posture Detection during Screen-Reading

Min

Cui

Han

et al. 2018

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Bodies lying on the ground may have arbitrary positions and configurations and may suffer from severe perspective distortions. Papers published in this area have mainly focused on two applications: fall detection [5]- [7], [15] and victim localization for rescue missions [25]. Mirmahboub et al [22] proposed a low-cost and easy-to-implement video-based system for human fall detection.…”

Section: B Lying Pose Detectionmentioning

confidence: 99%

“…Lying pose detection has important uses in numerous applications [14]. One such application is fall detection for elders and persons with disabilities living in smart homes [5], [7], [22]. A 2012 World Health Organization report revealed that falls are the second-leading cause of accidental-injury deaths worldwide and that every year, no fewer than 37 million falls are severe enough to require medical attention.…”

Section: Introductionmentioning

confidence: 99%

Automatic Dataset Expansion With Structured Feature Learning for Human Lying Pose Detection

et al. 2020

View full text Add to dashboard Cite

In this study, we developed a framework to localize human lying poses by a camera positioned above. Our framework is motivated by the fact that detecting lying poses is fundamentally more difficult than detecting pedestrians or localizing nondeformable objects such as cars, roads, and buildings due to the large number of poses, orientations, and scales that a human lying on the ground can take. An important problem with lying pose detection is the training dataset, which hardly accounts for each possible body configuration. As a solution, we propose a geometric expansion procedure that uses a virtual camera to increase the number of training images. We also use a Gibbs sampler to generate more training samples in the feature space on which the system can train its model. Once the training is completed, detection is performed on a multiscale and multirotational space. Because our framework accommodates a variety of object detection systems, we report the results for the Faster R-CNN, FPN, and RefineDet models. The results show that using automatic dataset expansion models systematically improves the results. INDEX TERMS Human lying pose detection, automatic dataset expansion, perspective transformation, gibbs sampling, deep learning.

show abstract

“…When the embedded devices are used the system is mostly used in indoor environment. Usually wearable sensors are used to monitor the person and track their movements and record them [18]. The sensors such as accelerometers, gyroscope, PIR, hybrid sensors, pressure sensors are also available in smart phones.…”

Section: Background Studymentioning

confidence: 99%

Detection of fall using Embedded Device and Machine Learning Implementation

Sreenidhi*,

Sneha,

Satyanarayana

2019

IJITEE

View full text Add to dashboard Cite

The health issues caused due to the abnormal and accidental falls increasing every day, some falls are even leading to death or fatal injuries. Such falls can cause trauma both physically and psychologically. To overcome these circumstances fall detection has become an important topic for researchers and scientists to provide better and effective solution. A proper detection of fall can save a life of human being be it any age by giving immediate required treatment. Generally alerting the concerned authorities regarding the fall happens to be crucial in the fall detection systems. There are many existing systems that tend to this problem but they all are heavily equipped and have some drawbacks. In this proposed system Raspberry pi4 is used with OpenCV for using MOG2 machine learning algorithm to detect the fall by concentrating only on the person. And for alerting the fall this system uses internet based REST API called TWILIO.

show abstract

Detection of Human Falls on Furniture Using Scene Analysis Based on Deep Learning and Activity Characteristics

Cited by 83 publications

References 40 publications

A Scene Recognition and Semantic Analysis Approach to Unhealthy Sitting Posture Detection during Screen-Reading

A Scene Recognition and Semantic Analysis Approach to Unhealthy Sitting Posture Detection during Screen-Reading

Automatic Dataset Expansion With Structured Feature Learning for Human Lying Pose Detection

Detection of fall using Embedded Device and Machine Learning Implementation

Contact Info

Product

Resources

About