Edge computing-based person detection system for top view surveillance: Using CenterNet with transfer learning

2021 ◽  
pp. 107489
Author(s):  
Imran Ahmed ◽  
Misbah Ahmad ◽  
Joel J.P.C. Rodrigues ◽  
Gwanggil Jeon
Keyword(s):  
Transfer Learning ◽  
Detection System ◽  
Edge Computing ◽  
Person Detection ◽  
Top View

scholarly journals A Remote Sensing and Airborne Edge-Computing Based Detection System for Pine Wilt Disease

IEEE Access ◽  
2021 ◽  
pp. 1-1
Author(s):  
Fengdi Li ◽  
Zhenyu Liu ◽  
Weixing Shen ◽  
Yan Wang ◽  
Yunlu Wang ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Detection System ◽  
Pine Wilt Disease ◽  
Wilt Disease ◽  
Edge Computing ◽  
Pine Wilt

scholarly journals Computer-Aided Colon Polyp Detection on High Resolution Colonoscopy Using Transfer Learning Techniques

Sensors ◽  
2021 ◽  
Vol 21 (16) ◽  
pp. 5315
Author(s):  
Chia-Pei Tang ◽  
Kai-Hong Chen ◽  
Tu-Liang Lin
Keyword(s):  
Real Time ◽  
Transfer Learning ◽  
Early Recognition ◽  
Detection System ◽  
Colon Polyp ◽  
Colon Polyps ◽  
Polyp Detection ◽  
Detection Model ◽  
Real Time Detection ◽  
Polyp Type

Colonoscopies reduce the incidence of colorectal cancer through early recognition and resecting of the colon polyps. However, the colon polyp miss detection rate is as high as 26% in conventional colonoscopy. The search for methods to decrease the polyp miss rate is nowadays a paramount task. A number of algorithms or systems have been developed to enhance polyp detection, but few are suitable for real-time detection or classification due to their limited computational ability. Recent studies indicate that the automated colon polyp detection system is developing at an astonishing speed. Real-time detection with classification is still a yet to be explored field. Newer image pattern recognition algorithms with convolutional neuro-network (CNN) transfer learning has shed light on this topic. We proposed a study using real-time colonoscopies with the CNN transfer learning approach. Several multi-class classifiers were trained and mAP ranged from 38% to 49%. Based on an Inception v2 model, a detector adopting a Faster R-CNN was trained. The mAP of the detector was 77%, which was an improvement of 35% compared to the same type of multi-class classifier. Therefore, our results indicated that the polyp detection model could attain a high accuracy, but the polyp type classification still leaves room for improvement.

scholarly journals An Automated Real-Time Face Mask Detection System Using Transfer Learning with Faster-RCNN in the Era of the COVID-19 Pandemic

2022 ◽  
Vol 71 (2) ◽  
pp. 4151-4166
Author(s):  
Maha Farouk S. Sabir ◽  
Irfan Mehmood ◽  
Wafaa Adnan Alsaggaf ◽  
Enas Fawai Khairullah ◽  
Samar Alhuraiji ◽  
...  
Keyword(s):  
Real Time ◽  
Transfer Learning ◽  
Detection System ◽  
Face Mask

New Swarm Intelligence Technique of Artificial Social Cockroaches for Suspicious Person Detection Using N-Gram Pixel With Visual Result Mining

2019 ◽  
pp. 545-570
Author(s):  
Hadj Ahmed Bouarara ◽  
Reda Mohamed Hamou ◽  
Abdelmalek Amine
Keyword(s):  
Detection System ◽  
Private Life ◽  
Graphical Form ◽  
Surveillance Video ◽  
Insect Behaviour ◽  
Public And Private ◽  
Person Detection ◽  
Surveillance Camera ◽  
N Gram ◽  
Representation Method

In the last decade, surveillance camera technology has become widely practiced in public and private places to ensure the safety of individuals. Merely, face to limits of violation the private life of people and the inability to identify malicious persons that hid their faces, finding a new policy of surveillance video has become compulsory. The authors' work deals on the development of a suspicious person detection system using a new insect behaviour algorithm called artificial social cockroaches ASC based on a new image representation method (n-gram pixel). It has as input a set of artificial cockroaches (human images) to classify them (hide) into shelters (classes) suspicious or normal depending on a set of aggregation rules (shelter darkness, congener's attraction and security quality). Their experiments were performed on a modified MuHAVi dataset and using the validation measures (recall, precision, f-measure, entropy and accuracy), in order to show the benefit derived from using such approach compared to the result of classical algorithms (KNN and C4.5). Finally, a visualisation step was achieved to see the results in graphical form with more realism for the purpose to help policeman, security associations and justice in their investigation.

scholarly journals Semi-Supervised Faster RCNN-Based Person Detection and Load Classification for Far Field Video Surveillance

2019 ◽  
Vol 1 (3) ◽  
pp. 756-767 ◽  
Author(s):  
Haoran Wei ◽  
Nasser Kehtarnavaz
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Transfer Learning ◽  
Video Data ◽  
Far Field ◽  
Neural Network Classifier ◽  
Computationally Efficient ◽  
Person Detection ◽  
Video Cameras ◽  
Processing Steps

This paper presents a semi-supervised faster region-based convolutional neural network (SF-RCNN) approach to detect persons and to classify the load carried by them in video data captured from distances several miles away via high-power lens video cameras. For detection, a set of computationally efficient image processing steps are considered to identify moving areas that may contain a person. These areas are then passed onto a faster RCNN classifier whose convolutional layers consist of ResNet50 transfer learning. Frame labels are obtained in a semi-supervised manner for the training of the faster RCNN classifier. For load classification, another convolutional neural network classifier whose convolutional layers consist of GoogleNet transfer learning is used to distinguish a person carrying a bundle from a person carrying a long arm. Despite the challenges associated with the video dataset examined in terms of the low resolution of persons, the presence of heat haze, and the shaking of the camera, it is shown that the developed approach outperforms the faster RCNN approach.

Sign in / Sign up

Export Citation Format

Share Document