scholarly journals Real-Time WebRTC based Mobile Surveillance System

2021 ◽  
Vol 11 (3) ◽  
Author(s):  
Alistair Baretto ◽  
Noel Pudussery ◽  
Veerasai Subramaniam ◽  
Amroz Siddiqui
Keyword(s):  
Object Detection ◽  
Real Time ◽  
Deep Neural Networks ◽  
Ease Of Use ◽  
Problem Statement ◽  
Wide Range ◽  
Technological Growth ◽  
Computationally Intensive ◽  
Processing Techniques ◽  
Opening Up

The rapid growth that has taken place in Computer Vision has been instrumental in driving the advancement of Image processing techniques and drawing inferences from them. Combined with the enormous capabilities that Deep Neural networks bring to the table, computers can be efficiently trained to automate the tasks and yield accurate and robust results quickly thus optimizing the process. Technological growth has enabled us to bring such computationally intensive tasks to lighter and lower-end mobile devices thus opening up a wide range of possibilities. WebRTC-the open-source web standard enables us to send multimedia-based data from peer to peer paving the way for Real-time Communication over the Web. With this project, we aim to build on one such opportunity that can enable us to perform custom object detection through an android based application installed on our mobile phones. Therefore, our problem statement is to be able to capture real-time feeds, perform custom object detection, generate inference results, and appropriately send intruder alerts when needed. To implement this, we propose a mobile-based over-the-cloud solution that can capitalize on the enormous and encouraging features of the YOLO algorithm and incorporate the functionalities of OpenCV’s DNN module for providing us with fast and correct inferences. Coupled with a good and intuitive UI, we can ensure ease of use of our application.

scholarly journals Real-time, low-latency closed-loop feedback using markerless posture tracking

2020 ◽  
Author(s):  
Gary Kane ◽  
Gonçalo Lopes ◽  
Jonny L. Saunders ◽  
Alexander Mathis ◽  
Mackenzie W. Mathis
Keyword(s):  
Real Time ◽  
Pose Estimation ◽  
Animal Behavior ◽  
Deep Neural Networks ◽  
Low Latency ◽  
Forward Prediction ◽  
Prediction Module ◽  
Wide Range ◽  
Loop Feedback ◽  
Closed Loop Feedback

AbstractThe ability to control a behavioral task or stimulate neural activity based on animal behavior in real-time is an important tool for experimental neuroscientists. Ideally, such tools are noninvasive, low-latency, and provide interfaces to trigger external hardware based on posture. Recent advances in pose estimation with deep learning allows researchers to train deep neural networks to accurately quantify a wide variety of animal behaviors. Here we provide a new DeepLabCut-Live! package that achieves low-latency real-time pose estimation (within 15 ms, >100 FPS), with an additional forward-prediction module that achieves zero-latency feedback, and a dynamic-cropping mode that allows for higher inference speeds. We also provide three options for using this tool with ease: (1) a stand-alone GUI (called DLC-Live! GUI), and integration into (2) Bonsai and (3) AutoPilot. Lastly, we benchmarked performance on a wide range of systems so that experimentalists can easily decide what hardware is required for their needs.

scholarly journals Low Complexity FFT Factorization for CS Reconstruction

2020 ◽  
Vol 9 (3) ◽  
pp. 438-442
Keyword(s):  
Real Time ◽  
High Speed ◽  
Performance Metrics ◽  
Matching Pursuit ◽  
Matrix Multiplication ◽  
Low Complexity ◽  
Orthogonal Matching Pursuit ◽  
Reconstruction Algorithms ◽  
Wide Range ◽  
Computationally Intensive

In this paper is presented a novel area efficient Fast Fourier transform (FFT) for real-time compressive sensing (CS) reconstruction. Among various methodologies used for CS reconstruction algorithms, Greedy-based orthogonal matching pursuit (OMP) approach provides better solution in terms of accurate implementation with complex computations overhead. Several computationally intensive arithmetic operations like complex matrix multiplication are required to formulate correlative vectors making this algorithm highly complex and power consuming hardware implementation. Computational complexity becomes very important especially in complex FFT models to meet different operational standards and system requirements. In general, for real time applications, FFT transforms are required for high speed computations as well as with least possible complexity overhead in order to support wide range of applications. This paper presents an hardware efficient FFT computation technique with twiddle factor normalization for correlation optimization in orthogonal matching pursuit (OMP). Experimental results are provided to validate the performance metrics of the proposed normalization techniques against complexity and energy related issues. The proposed method is verified by FPGA synthesizer, and validated with appropriate currently available comparative analyzes.

Adaptive Computation Reuse for Energy-Efficient Training of Deep Neural Networks

2021 ◽  
Vol 20 (6) ◽  
pp. 1-24
Author(s):  
Jason Servais ◽  
Ehsan Atoofian
Keyword(s):  
Neural Networks ◽  
Energy Efficiency ◽  
Deep Neural Networks ◽  
Power Budget ◽  
Adaptive Computation ◽  
Wide Range ◽  
Network Topologies ◽  
Computationally Intensive ◽  
High Degree ◽  
Degree Of Similarity

In recent years, Deep Neural Networks (DNNs) have been deployed into a diverse set of applications from voice recognition to scene generation mostly due to their high-accuracy. DNNs are known to be computationally intensive applications, requiring a significant power budget. There have been a large number of investigations into energy-efficiency of DNNs. However, most of them primarily focused on inference while training of DNNs has received little attention. This work proposes an adaptive technique to identify and avoid redundant computations during the training of DNNs. Elements of activations exhibit a high degree of similarity, causing inputs and outputs of layers of neural networks to perform redundant computations. Based on this observation, we propose Adaptive Computation Reuse for Tensor Cores (ACRTC) where results of previous arithmetic operations are used to avoid redundant computations. ACRTC is an architectural technique, which enables accelerators to take advantage of similarity in input operands and speedup the training process while also increasing energy-efficiency. ACRTC dynamically adjusts the strength of computation reuse based on the tolerance of precision relaxation in different training phases. Over a wide range of neural network topologies, ACRTC accelerates training by 33% and saves energy by 32% with negligible impact on accuracy.

scholarly journals Real Time Object Recognition and Classification using Deep Learning

2019 ◽  
pp. 355-359
Author(s):  
Kiruthiga N ◽  
Divya E ◽  
Haripriya R ◽  
Haripriya V.
Keyword(s):  
Deep Learning ◽  
Object Recognition ◽  
Object Detection ◽  
Real Time ◽  
Visually Impaired ◽  
Detection Algorithm ◽  
Indoor Environments ◽  
Wide Range ◽  
Impaired Person ◽  
First Time

Navigation in indoor environments is highly challenging for visually impaired person, particularly in spaces visited for the first time. Various solutions have been proposed to deal with this challenge. In this project consider as the real time object Recognition and classification using deep learning algorithms. Object detection mainly deals with identification of real time objects such as people, animals, and objects. Object detection algorithm uses a wide range of image processing applications for extracting the object's desired portion. This enables one to identify the objects and calculate the accuracy of the object and deliver through voice. Using this information, the system determines the user's trajectory and can locate possible obstacles in that route.

scholarly journals YOLO with adaptive frame control for real-time object detection applications

2021 ◽  
Author(s):  
Jeonghun Lee ◽  
Kwang-il Hwang
Keyword(s):  
Embedded Systems ◽  
Object Detection ◽  
Real Time ◽  
High Performance ◽  
Resource Constraints ◽  
Ease Of Use ◽  
Real Time Processing ◽  
Time Processing ◽  
Service Delay ◽  
Detection Software

AbstractYou only look once (YOLO) is being used as the most popular object detection software in many intelligent video applications due to its ease of use and high object detection precision. In addition, in recent years, various intelligent vision systems based on high-performance embedded systems are being developed. Nevertheless, the YOLO still requires high-end hardware for successful real-time object detection. In this paper, we first discuss real-time object detection service of the YOLO on AI embedded systems with resource constraints. In particular, we point out the problems related to real-time processing in YOLO object detection associated with network cameras, and then propose a novel YOLO architecture with adaptive frame control (AFC) that can efficiently cope with these problems. Through various experiments, we show that the proposed AFC can maintain the high precision and convenience of YOLO, and provide real-time object detection service by minimizing total service delay, which remains a limitation of the pure YOLO.

scholarly journals Fast Deep Neural Networks With Knowledge Guided Training and Predicted Regions of Interests for Real-Time Video Object Detection

IEEE Access ◽  
2018 ◽  
Vol 6 ◽  
pp. 8990-8999 ◽  
Author(s):  
Wenming Cao ◽  
Jianhe Yuan ◽  
Zhihai He ◽  
Zhi Zhang ◽  
Zhiquan He
Keyword(s):  
Neural Networks ◽  
Object Detection ◽  
Real Time ◽  
Deep Neural Networks ◽  
Video Object

Real-time cardiac monitoring through the development of a smart holter to detect pathologies through an expert algorithm (Preprint)

2020 ◽  
Author(s):  
Daniel Carreres-Prieto ◽  
Fernando Cerdán-Cartagena ◽  
Juan Suardiaz-Muro ◽  
Andrés Cabrera-Lozoya
Keyword(s):  
Atrial Fibrillation ◽  
Success Rate ◽  
Real Time ◽  
Medical Practice ◽  
Ease Of Use ◽  
Cardiac Monitoring ◽  
High Success Rate ◽  
Signal Quality ◽  
Portable Devices ◽  
Wide Range

BACKGROUND Constant monitoring of the heart’s state is essential for the early detection of pathologies. In the past, this analysis could only be carried out in hospitals, using sophisticated equipment handled by qualified staff. Today there is a wide range of portable monitoring devices (Holters) on the market but with a set of drawbacks (low number of leads supported and their low signal quality among others) that make it difficult to consider them as a viable replacement for the equipment used in medical practice OBJECTIVE This article describes the process of designing and implementing a Smart Holter able to record up to six leads at the same time, providing a signal quality comparable to the equipment used in medical practice, but with the dimensions, consumption and ease of use of portable devices. We also describe the workings of the expert algorithm for detecting cardiac anomalies in real time monitoring, which is embedded in the device itself, and which is capable of detecting tachycardia, bradycardia, ischemia and atrial fibrillation episodes with a high success rate. METHODS The hardware developed, performs the acquisition of 6 leads simultaneously, with a signal quality comparable to that of equipment used in medical practice. Each of the signals are processed by the algorithm described in this paper. This algorithm decomposes each lead into each heartbeat and extracts each of the segments that compose it (QRS complex) as well as a series of additional parameters. Based on the duration, amplitude and different thresholds, the system is able to detect with a high success rate, the existence of a certain cardiac pathology. RESULTS Performance evaluation shows the capacity of the Smart Holter devised to offer a high quality signal that combined with an embedded expert algorithm is capable of detecting tachycardia, bradycardia, ischemia and atrial fibrillation episodes in real time with a high success rate. CONCLUSIONS Development presented in this paper offers better characteristics, because it resolves a wide range of drawbacks inherent in that type of portable medical equipment, mainly in terms of signal quality. One aspect to highlight is the improvement in noise immunity of the equipment. Although it is not possible to compensate large artefacts produced while playing sports, which still remains a challenge for current monitoring systems, an important step has been taken in the right direction to achieve even greater attenuation in the future, through the use of dynamic filtering systems controlled digitally, unlike the systems currently present on the market.

scholarly journals Real-time, low-latency closed-loop feedback using markerless posture tracking

eLife ◽  
2020 ◽  
Vol 9 ◽  
Author(s):  
Gary A Kane ◽  
Gonçalo Lopes ◽  
Jonny L Saunders ◽  
Alexander Mathis ◽  
Mackenzie W Mathis
Keyword(s):  
Real Time ◽  
Pose Estimation ◽  
Animal Behavior ◽  
Deep Neural Networks ◽  
Low Latency ◽  
Forward Prediction ◽  
Prediction Module ◽  
Wide Range ◽  
Loop Feedback ◽  
Closed Loop Feedback

The ability to control a behavioral task or stimulate neural activity based on animal behavior in real-time is an important tool for experimental neuroscientists. Ideally, such tools are noninvasive, low-latency, and provide interfaces to trigger external hardware based on posture. Recent advances in pose estimation with deep learning allows researchers to train deep neural networks to accurately quantify a wide variety of animal behaviors. Here, we provide a new <monospace>DeepLabCut-Live!</monospace> package that achieves low-latency real-time pose estimation (within 15 ms, >100 FPS), with an additional forward-prediction module that achieves zero-latency feedback, and a dynamic-cropping mode that allows for higher inference speeds. We also provide three options for using this tool with ease: (1) a stand-alone GUI (called <monospace>DLC-Live! GUI</monospace>), and integration into (2) <monospace>Bonsai,</monospace> and (3) <monospace>AutoPilot</monospace>. Lastly, we benchmarked performance on a wide range of systems so that experimentalists can easily decide what hardware is required for their needs.

Sign in / Sign up

Export Citation Format

Share Document