A Skeleton-Free Fall Detection System From Depth Images Using Random Decision Forest

Abobakr, Ahmed; Hossny, Mohammed; Nahavandi, Saeid

doi:10.1109/jsyst.2017.2780260

Cited by 78 publications

(42 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Intelligent autonomous systems will greatly depend on replication of the senses that we, humans, use to cooperate with others and learn in an adaptive manner [26,27]. Computer vision [28], combined with deep learning [29], reinforcement learning, and GPU-based computation [30], has shown great promise in replicating primitive vision and sensory capabilities. However, for Industry 5.0 cobots, these capabilities must be improved significantly.…”

Section: Advances In Sensing Technologies and Machine Cognitionmentioning

confidence: 99%

Industry 5.0—A Human-Centric Solution

2019

Self Cite

View full text Add to dashboard Cite

Staying at the top is getting tougher and more challenging due to the fast-growing and changing digital technologies and AI-based solutions. The world of technology, mass customization, and advanced manufacturing is experiencing a rapid transformation. Robots are becoming even more important as they can now be coupled with the human mind by means of brain–machine interface and advances in artificial intelligence. A strong necessity to increase productivity while not removing human workers from the manufacturing industry is imposing punishing challenges on the global economy. To counter these challenges, this article introduces the concept of Industry 5.0, where robots are intertwined with the human brain and work as collaborator instead of competitor. This article also outlines a number of key features and concerns that every manufacturer may have about Industry 5.0. In addition, it presents several developments achieved by researchers for use in Industry 5.0 applications and environments. Finally, the impact of Industry 5.0 on the manufacturing industry and overall economy is discussed from an economic and productivity point of view, where it is argued that Industry 5.0 will create more jobs than it will take away.

show abstract

Section: Advances In Sensing Technologies and Machine Cognitionmentioning

confidence: 99%

Industry 5.0—A Human-Centric Solution

2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Fall detection and prevention is a growing concerns among public health where there is a shortage in datasets of realistic fall posture sequences. These datasets are usually recorded by stunt actors who can fall safely or generated by 3D artists [58]. However, both solutions do provide data that is not a real representation of fall occurrences.…”

Section: Resultsmentioning

confidence: 99%

Just Don’t Fall: An AI Agent’s Learning Journey Towards Posture Stabilisation

Hossny

Iskander

2020

Self Cite

View full text Add to dashboard Cite

Learning to maintain postural balance while standing requires a significant, fine coordination effort between the neuromuscular system and the sensory system. It is one of the key contributing factors towards fall prevention, especially in the older population. Using artificial intelligence (AI), we can similarly teach an agent to maintain a standing posture, and thus teach the agent not to fall. In this paper, we investigate the learning progress of an AI agent and how it maintains a stable standing posture through reinforcement learning. We used the Deep Deterministic Policy Gradient method (DDPG) and the OpenSim musculoskeletal simulation environment based on OpenAI Gym. During training, the AI agent learnt three policies. First, it learnt to maintain the Centre-of-Gravity and Zero-Moment-Point in front of the body. Then, it learnt to shift the load of the entire body on one leg while using the other leg for fine tuning the balancing action. Finally, it started to learn the coordination between the two pre-trained policies. This study shows the potentials of using deep reinforcement learning in human movement studies. The learnt AI behaviour also exhibited attempts to achieve an unplanned goal because it correlated with the set goal (e.g., walking in order to prevent falling). The failed attempts to maintain a standing posture is an interesting by-product which can enrich the fall detection and prevention research efforts.

show abstract

“…This approach estimates the visibility of pedestrian parts at multiple layers and learns their relationship with a discriminative deep model. This method was further expanded using a so-called joint deep learning [24], [43], whose goal is to jointly learn the pedestrian parts to maximize their strengths through cooperation. Sermanet et al [47] presented an integrated convolutional network (convnet) framework for classifying, localizing, and detecting human shapes with a novel approach for learning to predict the object boundaries.…”

Section: Related Work a Pedestrian Detectionmentioning

confidence: 99%

“…Although this task has long been studied [1], [2], only recently have scientific breakthroughs combined with more processing power led to market-ready solutions [19]. Among the most frequently used object detection systems are those that focus on pedestrians [3], [20] and face detection [4], [24]. Despite these successful attempts, object detection remains an open problem for numerous applications.…”

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

A Skeleton-Free Fall Detection System From Depth Images Using Random Decision Forest

Cited by 78 publications

References 40 publications

Industry 5.0—A Human-Centric Solution

Industry 5.0—A Human-Centric Solution

Just Don’t Fall: An AI Agent’s Learning Journey Towards Posture Stabilisation

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

Contact Info

Product

Resources

About