MotionRec: A Unified Deep Framework for Moving Object Recognition

Mandal, Murari; Kumar, Lav Kush; Saran, Mahipal Singh; Vipparthi, Santosh Kumar

doi:10.1109/wacv45572.2020.9093324

Cited by 27 publications

(16 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mandal M, et al [13] has presented a novel deep learning framework which performs online moving object detection while streaming videos. Pixel-wise binary segmentations were previously done whereas the OR technique does not distinguish between moving or static objects.…”

Section: Related Workmentioning

confidence: 99%

“…Pixel-wise binary segmentations were previously done whereas the OR technique does not distinguish between moving or static objects. At first Mandal M [13] has attempted to classify moving parts of the video and they have achieved this by labelling axis aligned bounding boxes for moving objects which requires less computational resources than producing pixel-level estimates. In their proposed MotionRec framework [13], they have learned both temporal and spatial features using past history and current frames respectively.…”

Section: Related Workmentioning

confidence: 99%

“…From the motion saliency maps feature pyramids have been developed which performs regression and classification of fetched data. This framework [13] works online which requires few frames. The authors have 42614 objects in 24923 video frames.…”

Section: Related Workmentioning

confidence: 99%

“…One of the most promising fields of computer vision is moving object detection. For this motion rec [13] is a model that serves as one of the best framework for the recognition of objects from video. Here temporal information through multiple frames serves as the key role to understand the features of different objects.…”

Section: B Video Object Detectionmentioning

confidence: 99%

See 3 more Smart Citations

Detection of Human Behaviour byObject Recognitionusing Deep Learning:A Review

Mukherjee¹,

Bandyopadhyay²

2020

IJIRCST

View full text Add to dashboard Cite

The major drawback of the society is the falsehood of human nature; so prediction of nature of the individual by analysing the video or image of that person is highly necessary. From the post World War II period due to the advancement of technology since the past few decades many countries have developed low cost cameras with high resolution. They generally use the RGB and depth features to enhance the image quality captured by the camera. Hence object recognition is the new branch of computer science which emerges. It has got a close relationship with image understanding and analysis of video; which encourages several researchers to work in this domain since past few years. As the branch of deep learning develops handful of efficient tools have been develop which prove to be highly efficient to learn high level deeper features of the image and semantics. In this paper a review on object recognition using deep learning has been discussed. This paper includes basics of deep learning and object recognition. Then we have discussed some tools required to perform object recognition as well as moving object recognition and finally some future goals of this subject have been discussed.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: B Video Object Detectionmentioning

confidence: 99%

See 2 more Smart Citations

Detection of Human Behaviour byObject Recognitionusing Deep Learning:A Review

Mukherjee¹,

Bandyopadhyay²

2020

IJIRCST

View full text Add to dashboard Cite

show abstract

“…Hence, this work is focused on discussing ML-based solutions for remote monitoring of vital signs which can be run or deployed using simple cameras available on a smartphone or laptop. Artificial intelligence has come a long way from being effective in limited applications [14,47,48], to having a transformative impact across numerous domains [1,20,26,28,38,49,53,57,58]. Artificial Intelligence (AI) has been revolutionizing multiple fields like Drones [24],VANETs [36], and IoT Security [35].…”

Section: Introductionmentioning

confidence: 99%

AI-enabled remote monitoring of vital signs for COVID-19: methods, prospects and challenges

et al. 2021

View full text Add to dashboard Cite

The COVID-19 pandemic has overwhelmed the existing healthcare infrastructure in many parts of the world. Healthcare professionals are not only over-burdened but also at a high risk of nosocomial transmission from COVID-19 patients. Screening and monitoring the health of a large number of susceptible or infected individuals is a challenging task. Although professional medical attention and hospitalization are necessary for high-risk COVID-19 patients, home isolation is an effective strategy for low and medium risk patients as well as for those who are at risk of infection and have been quarantined. However, this necessitates effective techniques for remotely monitoring the patients’ symptoms. Recent advances in Machine Learning (ML) and Deep Learning (DL) have strengthened the power of imaging techniques and can be used to remotely perform several tasks that previously required the physical presence of a medical professional. In this work, we study the prospects of vital signs monitoring for COVID-19 infected as well as quarantined individuals by using DL and image/signal-processing techniques, many of which can be deployed using simple cameras and sensors available on a smartphone or a personal computer, without the need of specialized equipment. We demonstrate the potential of ML-enabled workflows for several vital signs such as heart and respiratory rates, cough, blood pressure, and oxygen saturation. We also discuss the challenges involved in implementing ML-enabled techniques.

show abstract