Spatial-temporal Regularized Multi-modality Correlation Filters for Tracking with Re-detection

2021 ◽  
Vol 17 (2) ◽  
pp. 1-16
Author(s):  
Xiangyuan Lan ◽  
Zifei Yang ◽  
Wei Zhang ◽  
Pong C. Yuen
Keyword(s):  
Learning Algorithm ◽  
Detection Algorithm ◽  
Correlation Filter ◽  
Appearance Modeling ◽  
Dynamic Background ◽  
Multiple Modalities ◽  
Image Sensing ◽  
Sensing Technology ◽  
Weight Learning ◽  
Appearance Changes

The development of multi-spectrum image sensing technology has brought great interest in exploiting the information of multiple modalities (e.g., RGB and infrared modalities) for solving computer vision problems. In this article, we investigate how to exploit information from RGB and infrared modalities to address two important issues in visual tracking: robustness and object re-detection. Although various algorithms that attempt to exploit multi-modality information in appearance modeling have been developed, they still face challenges that mainly come from the following aspects: (1) the lack of robustness to deal with large appearance changes and dynamic background, (2) failure in re-capturing the object when tracking loss happens, and (3) difficulty in determining the reliability of different modalities. To address these issues and perform effective integration of multiple modalities, we propose a new tracking-by-detection algorithm called Adaptive Spatial-temporal Regulated Multi-Modality Correlation Filter. Particularly, an adaptive spatial-temporal regularization is imposed into the correlation filter framework in which the spatial regularization can help to suppress effect from the cluttered background while the temporal regularization enables the adaptive incorporation of historical appearance cues to deal with appearance changes. In addition, a dynamic modality weight learning algorithm is integrated into the correlation filter training, which ensures that more reliable modalities gain more importance in target tracking. Experimental results demonstrate the effectiveness of the proposed method.

scholarly journals Gait Phase Detection Based on Muscle Deformation with Static Standing-Based Calibration

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1081
Author(s):  
Tamon Miyake ◽  
Shintaro Yamamoto ◽  
Satoshi Hosono ◽  
Satoshi Funabashi ◽  
Zhengxue Cheng ◽  
...  
Keyword(s):  
Learning Algorithm ◽  
Detection System ◽  
Calibration Method ◽  
Detection Algorithm ◽  
Video Data ◽  
Detection Accuracy ◽  
Phase Detection ◽  
Gait Phase ◽  
Logistic Regression Algorithm ◽  
Short Time

Gait phase detection, which detects foot-contact and foot-off states during walking, is important for various applications, such as synchronous robotic assistance and health monitoring. Gait phase detection systems have been proposed with various wearable devices, sensing inertial, electromyography, or force myography information. In this paper, we present a novel gait phase detection system with static standing-based calibration using muscle deformation information. The gait phase detection algorithm can be calibrated within a short time using muscle deformation data by standing in several postures; it is not necessary to collect data while walking for calibration. A logistic regression algorithm is used as the machine learning algorithm, and the probability output is adjusted based on the angular velocity of the sensor. An experiment is performed with 10 subjects, and the detection accuracy of foot-contact and foot-off states is evaluated using video data for each subject. The median accuracy is approximately 90% during walking based on calibration for 60 s, which shows the feasibility of the static standing-based calibration method using muscle deformation information for foot-contact and foot-off state detection.

IMPROVED TOW-END DETECTION FOR FIBER PLACEMENT INSPECTION USING MACHINE LEARNING

2021 ◽  
Author(s):  
ADRIANA W. (AGNES) BLOM-SCHIEBER ◽  
WEI GUO ◽  
EKTA SAMANI ◽  
ASHIS BANERJEE
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
Image Data ◽  
Detection Algorithm ◽  
Automated Inspection ◽  
Machine Learning Algorithm ◽  
Fiber Placement ◽  
Inspection Systems ◽  
Automated Fiber Placement ◽  
The University

A machine learning approach to improve the detection of tow ends for automated inspection of fiber-placed composites is presented. Automated inspection systems for automated fiber placement processes have been introduced to reduce the time it takes to inspect plies after they are laid down. The existing system uses image data from ply boundaries and a contrast-based algorithm to locate the tow ends in these images. This system fails to recognize approximately 10% of the tow ends, which are then presented to the operator for manual review, taking up precious time in the production process. An improved tow end detection algorithm based on machine learning is developed through a research project with the Boeing Advanced Research Center (BARC) at the University of Washington. This presentation shows the preprocessing, neural network and post‐processing steps implemented in the algorithm, and the results achieved with the machine learning algorithm. The machine learning algorithm resulted in a 90% reduction in the number of undetected tows compared to the existing system.

scholarly journals Light People: Professor Aydogan Ozcan

2021 ◽  
Vol 10 (1) ◽  
Author(s):  
Tingting Sun
Keyword(s):  
Deep Learning ◽  
Los Angeles ◽  
Learning Algorithm ◽  
Computational Imaging ◽  
Technological Innovations ◽  
Image Generation ◽  
Sensing Technology ◽  
Reconstruction Methods ◽  
New Ideas ◽  
The University

EditorialIn 2016, the news that Google’s artificial intelligence (AI) robot AlphaGo, based on the principle of deep learning, won the victory over lee Sedol, the former world Go champion and the famous 9th Dan competitor of Korea, caused a sensation in both fields of AI and Go, which brought epoch-making significance to the development of deep learning. Deep learning is a complex machine learning algorithm that uses multiple layers of artificial neural networks to automatically analyze signals or data. At present, deep learning has penetrated into our daily life, such as the applications of face recognition and speech recognition. Scientists have also made many remarkable achievements based on deep learning. Professor Aydogan Ozcan from the University of California, Los Angeles (UCLA) led his team to research deep learning algorithms, which provided new ideas for the exploring of optical computational imaging and sensing technology, and introduced image generation and reconstruction methods which brought major technological innovations to the development of related fields. Optical designs and devices are moving from being physically driven to being data-driven. We are much honored to have Aydogan Ozcan, Fellow of the National Academy of Inventors and Chancellor’s Professor of UCLA, to unscramble his latest scientific research results and foresight for the future development of related fields, and to share his journey of pursuing Optics, his indissoluble relationship with Light: Science & Applications (LSA), and his experience in talent cultivation.

scholarly journals Moving Objects Detection & Recognition using Hybrid Canny Edge Detection Algorithm in Digital Image Processing

2019 ◽  
Vol 8 (9S3) ◽  
pp. 56-60
Keyword(s):  
Object Detection ◽  
Moving Objects ◽  
Detection Method ◽  
Learning Algorithm ◽  
Detection Algorithm ◽  
Moving Objects Detection ◽  
Canny Edge ◽  
Objects Detection ◽  
Canny Edge Detection Algorithm ◽  
Day By Day

Recognition and detection of an object in the watched scenes is a characteristic organic capacity. Animals and human being play out this easily in day by day life to move without crashes, to discover sustenance, dodge dangers, etc. Be that as it may, comparable PC techniques and calculations for scene examination are not all that direct, in spite of their exceptional advancement. Object detection is the process in which finding or recognizing cases of articles (for instance faces, mutts or structures) in computerized pictures or recordings. This is the fundamental task in computer. For detecting the instance of an object and to pictures having a place with an article classification object detection method usually used learning algorithm and extracted features. This paper proposed a method for moving object detection and vehicle detection.

scholarly journals Improved Antibiotic Detection in Raw Milk Using Machine Learning Tools over the Absorption Spectra of a Problem-Specific Nanobiosensor

Sensors ◽  
2020 ◽  
Vol 20 (16) ◽  
pp. 4552
Author(s):  
Pablo Gutiérrez ◽  
Sebastián E. Godoy ◽  
Sergio Torres ◽  
Patricio Oyarzún ◽  
Ignacio Sanhueza ◽  
...  
Keyword(s):  
Machine Learning ◽  
Milk Sample ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Raw Milk ◽  
Detection Algorithm ◽  
Learning Tools ◽  
Antibiotic Detection ◽  
Biosensor System ◽  
Spectral Detection

In this article we present the development of a biosensor system that integrates nanotechnology, optomechanics and a spectral detection algorithm for sensitive quantification of antibiotic residues in raw milk of cow. Firstly, nanobiosensors were designed and synthesized by chemically bonding gold nanoparticles (AuNPs) with aptamer bioreceptors highly selective for four widely used antibiotics in the field of veterinary medicine, namely, Kanamycin, Ampicillin, Oxytetracycline and Sulfadimethoxine. When molecules of the antibiotics are present in the milk sample, the interaction with the aptamers induces random AuNP aggregation. This phenomenon modifies the initial absorption spectrum of the milk sample without antibiotics, producing spectral features that indicate both the presence of antibiotics and, to some extent, its concentration. Secondly, we designed and constructed an electro-opto-mechanic device that performs automatic high-resolution spectral data acquisition in a wavelength range of 400 to 800 nm. Thirdly, the acquired spectra were processed by a machine-learning algorithm that is embedded into the acquisition hardware to determine the presence and concentration ranges of the antibiotics. Our approach outperformed state-of-the-art standardized techniques (based on the 520/620 nm ratio) for antibiotic detection, both in speed and in sensitivity.

scholarly journals A Fast Learning Method for Accurate and Robust Lane Detection Using Two-Stage Feature Extraction with YOLO v3

Sensors ◽  
2018 ◽  
Vol 18 (12) ◽  
pp. 4308 ◽  
Author(s):  
Xiang Zhang ◽  
Wei Yang ◽  
Xiaolin Tang ◽  
Jie Liu
Keyword(s):  
Learning Algorithm ◽  
Structural Parameters ◽  
Feature Learning ◽  
Automatic Generation ◽  
Detection Algorithm ◽  
Lane Detection ◽  
Stage Model ◽  
Two Stage ◽  
Label Data ◽  
Second Stage

To improve the accuracy of lane detection in complex scenarios, an adaptive lane feature learning algorithm which can automatically learn the features of a lane in various scenarios is proposed. First, a two-stage learning network based on the YOLO v3 (You Only Look Once, v3) is constructed. The structural parameters of the YOLO v3 algorithm are modified to make it more suitable for lane detection. To improve the training efficiency, a method for automatic generation of the lane label images in a simple scenario, which provides label data for the training of the first-stage network, is proposed. Then, an adaptive edge detection algorithm based on the Canny operator is used to relocate the lane detected by the first-stage model. Furthermore, the unrecognized lanes are shielded to avoid interference in subsequent model training. Then, the images processed by the above method are used as label data for the training of the second-stage model. The experiment was carried out on the KITTI and Caltech datasets, and the results showed that the accuracy and speed of the second-stage model reached a high level.

scholarly journals Classification of Shellfish Recognition Based on Improved Faster R-CNN Framework of Deep Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Yiran Feng ◽  
Xueheng Tao ◽  
Eung-Joo Lee
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
Experimental Tests ◽  
Detection Algorithm ◽  
Detection Accuracy ◽  
Multiple Objects ◽  
Detection Model ◽  
Deep Learning Algorithm ◽  
Quality Sorting

In view of the current absence of any deep learning algorithm for shellfish identification in real contexts, an improved Faster R-CNN-based detection algorithm is proposed in this paper. It achieves multiobject recognition and localization through a second-order detection network and replaces the original feature extraction module with DenseNet, which can fuse multilevel feature information, increase network depth, and avoid the disappearance of network gradients. Meanwhile, the proposal merging strategy is improved with Soft-NMS, where an attenuation function is designed to replace the conventional NMS algorithm, thereby avoiding missed detection of adjacent or overlapping objects and enhancing the network detection accuracy under multiple objects. By constructing a real contexts shellfish dataset and conducting experimental tests on a vision recognition seafood sorting robot production line, we were able to detect the features of shellfish in different scenarios, and the detection accuracy was improved by nearly 4% compared to the original detection model, achieving a better detection accuracy. This provides favorable technical support for future quality sorting of seafood using the improved Faster R-CNN-based approach.

scholarly journals Multicenter Validation of a Deep Learning Detection Algorithm for Focal Cortical Dysplasia

Neurology ◽  
2021 ◽  
pp. 10.1212/WNL.0000000000012698
Author(s):  
Ravnoor Singh Gill ◽  
Hyo-Min Lee ◽  
Benoit Caldairou ◽  
Seok-Jun Hong ◽  
Carmen Barba ◽  
...  
Keyword(s):  
Deep Learning ◽  
Risk Stratification ◽  
Learning Algorithm ◽  
Focal Cortical Dysplasia ◽  
Detection Algorithm ◽  
Cortical Dysplasia ◽  
False Positives ◽  
Class Iii ◽  
Deep Learning Algorithm ◽  
Independent Cohort

Objective.To test the hypothesis that a multicenter-validated computer deep learning algorithm detects MRI-negative focal cortical dysplasia (FCD).Methods.We used clinically-acquired 3D T1-weighted and 3D FLAIR MRI of 148 patients (median age, 23 years [range, 2-55]; 47% female) with histologically-verified FCD at nine centers to train a deep convolutional neural network (CNN) classifier. Images were initially deemed as MRI-negative in 51% of cases, in whom intracranial EEG determined the focus. For risk stratification, the CNN incorporated Bayesian uncertainty estimation as a measure of confidence. To evaluate performance, detection maps were compared to expert FCD manual labels. Sensitivity was tested in an independent cohort of 23 FCD cases (13±10 years). Applying the algorithm to 42 healthy and 89 temporal lobe epilepsy disease controls tested specificity.Results.Overall sensitivity was 93% (137/148 FCD detected) using a leave-one-site-out cross-validation, with an average of six false positives per patient. Sensitivity in MRI-negative FCD was 85%. In 73% of patients, the FCD was among the clusters with the highest confidence; in half it ranked the highest. Sensitivity in the independent cohort was 83% (19/23; average of five false positives per patient). Specificity was 89% in healthy and disease controls.Conclusions.This first multicenter-validated deep learning detection algorithm yields the highest sensitivity to date in MRI-negative FCD. By pairing predictions with risk stratification this classifier may assist clinicians to adjust hypotheses relative to other tests, increasing diagnostic confidence. Moreover, generalizability across age and MRI hardware makes this approach ideal for pre-surgical evaluation of MRI-negative epilepsy.Classification of evidence.This study provides Class III evidence that deep learning on multimodal MRI accurately identifies FCD in epilepsy patients initially diagnosed as MRI-negative.

Sign in / Sign up

Export Citation Format

Share Document