Recently, thermal cameras have been used in various fields, including surveillance systems and advanced driver assistance systems (ADAS), as they perform better in low light than visible-light cameras. Some challenges...
详细信息
ISBN:
(纸本)9798350307573;9798350307566
Recently, thermal cameras have been used in various fields, including surveillance systems and advanced driver assistance systems (ADAS), as they perform better in low light than visible-light cameras. Some challenges in the surveillance system or ADAS field related to thermal cameras are occlusion and thermal crossover between objects with similar appearances during object detection or object tracking tasks, which can lead to misdetection, false positives, and lost tracking. In this paper, performance analysis of you-only-look-once (YOLO) combined with deep online real-time tracking (DeepSORT) on thermal video-based online multi-object tracking (MOT) in occlusion and thermal crossover scene is presented. YOLO, as one of state-ofthe-art method for detection task, is used for detection system. Then, the detected object from YOLO is tracked using DeepSORT. The results demonstrate that the online MOT of sequential thermal images using YOLO-DeepSORT achieved a MOTA score of 44.2% and IDF1 of 45.3%. Thus, negative example was added in YOLO training process to reduce false detection, and it gives improvement with MOTA score of 63.8% and IDF1 score of 54.6%.
This study analyzes the utility of texture-based local binary pattern features to spot brain cancers. Local Binary pattern is a highly effective texture feature that uses a three-bythree sliding window to label the pi...
详细信息
The research study on the "Design and Implementation of an AI-Enhanced Mental Health Tool for Academic Stress"addresses the growing mental health crisis among students, particularly concerning academic press...
详细信息
The proceedings contain 70 papers. The special focus in this conference is on Deep Learning, Artificial intelligence and robotics. The topics include: A Short Survey on Comparative Study of Modern Cryptograp...
ISBN:
(纸本)9783031609343
The proceedings contain 70 papers. The special focus in this conference is on Deep Learning, Artificial intelligence and robotics. The topics include: A Short Survey on Comparative Study of Modern Cryptography Approach;advances in Computer-Aided Detection and Diagnosis of Retinal Diseases: A Comprehensive Survey of Fundal Image analysis;driver Safety and Drowsiness Detection in Internet of Vehicles with Federated Learning;privacy Preserving Fingerprint Classification Using Federated Learning;comparative Study of Ensemble Learning Models for Smart Meter Load;social-Media Video Summarization Using Convolutional Neural Network and Kohnen’s Self Organizing Map;machine Learning and Deep Leaning in Predicting Coronary Heart Disease;Augmented Super Resolution GAN (ASRGAN) for Image Enhancement Through Reinforced Discriminator;Convolutional Block Attention Assisted Dense Stacked Bi-LSTM for the Generation of RDF Statements;real-Time Permanent Change Proposals for Abandoned Object Detection;an Excursion to Ontology-Based Non-functional Requirements Specification;a Review of Traditional and Neural Network Methods for Protecting Privacy in Big Data Analytics;a Long Short-Term Memory Learning Based Malicious Node Detection for Clustering in Wireless Sensor Networks;experimental analysis for Sensor Reduction to Depict Real-Time Applications Through Regression Techniques;multi-resolution Neural Network for Road Scene Segmentation;A CNN-Based Road Accident Detection and Comparison of Classification Techniques;football Match Result Prediction Using Twitter Statistical/Historical Data;safeguarding Ecosystems and Efficiency in Peer-to-Peer File Sharing Systems: An IoT-Inspired Approach to Pollution Mitigation;a Heuristic for Minimizing Resource Requirement for Quantum Graph Neural Networks;Light-Gated Recurrent Unit Based Acoustic Modeling for Improved Hindi ASR;Detecting Phishing URLs Using Machine Learning: A Review;comparative analysis of Pneumonia Detection from Chest X-ray Using
A study is conducted on employees' perception of artificial intelligence in an organization's hiring process. The objective of the research is to find out how employees perceive the importance of artificial in...
详细信息
Pipelines are the key infrastructure for gas and liquid fossil energy, any leakage on the transportation pipelines lead to disasters for human safety and environment. The most popular method for the health monitoring ...
详细信息
ISBN:
(纸本)9798350344738;9798350344721
Pipelines are the key infrastructure for gas and liquid fossil energy, any leakage on the transportation pipelines lead to disasters for human safety and environment. The most popular method for the health monitoring of it is using pipeline inspection robots. The circumferential-deployed sensors capture two-dimensional data, i.e. visual images for defect analysis. However, due to the high vibration and harsh environment in pipelines, sensor failure becomes the common cases. Fixing this sensor failure is solving one visual data restoration problem, so this paper proposes one compressed sensing (CS)-based method. The core idea is that sampling a partial pixels in one image can full reconstruct the full image with CS theory, and the health sensor values are regarded as the CS sampling values. Block-byblock restoration scheme is used. The experimental results on real pipeline inspection data show our proposed CS method has better performance than the traditional interpolation method for most typical features, e.g. 20% of improvement on 2D coefficients with baseline for spiral weld, 53% of improvement on root-meansquare-error on defect region.
This paper explores the integration of Virtual Reality(VR) to a Surgical Robotic Simulation to enhance the quality of data used for training a ground-truth algorithm for surgical procedures performed by the DaVinci ro...
详细信息
This research investigates user trust in artificial intelligence (AI) applications based on empirical analysis of intelligent service robots in service industry. We examined the impacts of human-like design of AI robo...
详细信息
ISBN:
(纸本)9781665483834
This research investigates user trust in artificial intelligence (AI) applications based on empirical analysis of intelligent service robots in service industry. We examined the impacts of human-like design of AI robots on intelligence and anthropomorphism perceived by users. The relationships between perceived intelligence, perceived anthropomorphism, and level of trust were also tested. An online survey with a between-subject design was conducted to collect data. The results indicate that robots with physical human-like appearance were perceived lower level of anthropomorphism and intelligence, and interaction function design on robots does not significantly increase those perceptions. Moreover, the significant effect of perceived intelligence on perceived anthropomorphism was confirmed, and both perceptions of users exert positive effect on their trust in AI robots.
Variable stiffness joints, due to their variable stiffness feature, have promising application prospects in fields such as human rehabilitation and military surveillance. However, currently, variable stiffness joints ...
详细信息
Collaborative robots boast high flexibility, reliable safety, and strong human-machine collaboration capabilities. However, in practical operations, axis tilt errors can lead to decreased end-effector positioning accu...
详细信息
ISBN:
(纸本)9789819607709;9789819607716
Collaborative robots boast high flexibility, reliable safety, and strong human-machine collaboration capabilities. However, in practical operations, axis tilt errors can lead to decreased end-effector positioning accuracy, thereby affecting work performance and quality. To address this issue, this paper presents a kinematic model for collaborative robots that integrates Denavit-Hartenberg (DH) parameter errors with axis tilt errors. Initially referencing the DH method, the model establishes both the robot's kinematic model and a parameter error model. It addresses issues unresolved by traditional non-geometric error compensation methods, namely the inability to establish a mapping relationship between the axis tilt joint positions in the calibration coordinate system and the end-effector positional errors. By utilizing the DH method and incorporating a generalized error matrix model, an improved kinematic model that includes tilt errors is proposed. This paper conducts forward kinematic analysis and employs the Newton-Raphson iteration method for inverse kinematics solutions. Simulation and experimental results demonstrate that, regardless of the influence of the tilt error matrix, the model accurately and effectively determines the end-effector pose and joint angles of the collaborative robot.
暂无评论