scholarly journals A New Ball Detection Strategy for Enhancing the Performance of Ball Bees Based on Fuzzy Inference Engine

2021 ◽  
Author(s):  
Arwa Abulwafa ◽  
Ahmed I. Saleh ◽  
Mohamed S. Saraya ◽  
Hesham A. Ali
Keyword(s):  
Moving Objects ◽  
Fuzzy Inference ◽  
Research Area ◽  
Color Contrast ◽  
Detection Techniques ◽  
Testing Stage ◽  
Partially Occluded ◽  
Ball Detection ◽  
Mixture Of Gaussian ◽  
Poor Lighting

Abstract Sports video analysis has received much attention as it is turned to be a hot research area in the field of image processing. This led to opportunities to develop fascinating applications supported by analysis of different sports especially football. Identifying the ball in soccer images is an essential task for not only goal scoring but also players’ evaluation. However, soccer ball detection suffers from several hurdles such as; occlusions, fast moving objects, shadows, poor lighting, color contrast, and other static background objects. Although several ball detection techniques have been introduced such as; Frame Difference, Mixture of Gaussian (MoG), Optical Flow and etc., ball detection in soccer games is still an open research area. In this paper, a new Fuzzy Based Ball Detection (FB2D) strategy is proposed for identifying the ball through a set of image sequences extracted form a soccer match video. FB2D has the ability to accurately identify the ball even if it is attached to the white lines drawn on the playground or partially occluded behind players. FB2D has been compared to recent ball detection techniques. Experimental results have shown that FB2D outperforms recent detection techniques as it introduced the maximum accuracy and the accuracy of detection in the testing stage is close to 100%. As well as the minimum error.

FACE RECOGNITION USING FUZZY INFERENCE SYSTEM

2009 ◽  
Vol 8 (3) ◽  
pp. 887-897
Author(s):  
Vishal Paika ◽  
Er. Pankaj Bhambri
Keyword(s):  
Neural Networks ◽  
Fuzzy Inference ◽  
Facial Features ◽  
Facial Appearance ◽  
Feature Points ◽  
Inference System ◽  
Detection Techniques ◽  
The Face ◽  
Hair Style ◽  
Facial Images

The face is the feature which distinguishes a person. Facial appearance is vital for human recognition. It has certain features like forehead, skin, eyes, ears, nose, cheeks, mouth, lip, teeth etc which helps us, humans, to recognize a particular face from millions of faces even after a large span of time and despite large changes in their appearance due to ageing, expression, viewing conditions and distractions such as disfigurement of face, scars, beard or hair style. A face is not merely a set of facial features but is rather but is rather something meaningful in its form.In this paper, depending on the various facial features, a system is designed to recognize them. To reveal the outline of the face, eyes, ears, nose, teeth etc different edge detection techniques have been used. These features are extracted in the term of distance between important feature points. The feature set obtained is then normalized and are feed to artificial neural networks so as to train them for reorganization of facial images.

scholarly journals A Set of Single YOLO Modalities to Detect Occluded Entities via Viewpoint Conversion

2021 ◽  
Vol 11 (13) ◽  
pp. 6016
Author(s):  
Jinsoo Kim ◽  
Jeongho Cho
Keyword(s):  
Object Detection ◽  
Autonomous Vehicles ◽  
Autonomous Driving ◽  
Detection Algorithm ◽  
Detection Accuracy ◽  
Cloud Data ◽  
Detection Techniques ◽  
Bounding Boxes ◽  
Partially Occluded ◽  
Rgb Image

For autonomous vehicles, it is critical to be aware of the driving environment to avoid collisions and drive safely. The recent evolution of convolutional neural networks has contributed significantly to accelerating the development of object detection techniques that enable autonomous vehicles to handle rapid changes in various driving environments. However, collisions in an autonomous driving environment can still occur due to undetected obstacles and various perception problems, particularly occlusion. Thus, we propose a robust object detection algorithm for environments in which objects are truncated or occluded by employing RGB image and light detection and ranging (LiDAR) bird’s eye view (BEV) representations. This structure combines independent detection results obtained in parallel through “you only look once” networks using an RGB image and a height map converted from the BEV representations of LiDAR’s point cloud data (PCD). The region proposal of an object is determined via non-maximum suppression, which suppresses the bounding boxes of adjacent regions. A performance evaluation of the proposed scheme was performed using the KITTI vision benchmark suite dataset. The results demonstrate the detection accuracy in the case of integration of PCD BEV representations is superior to when only an RGB camera is used. In addition, robustness is improved by significantly enhancing detection accuracy even when the target objects are partially occluded when viewed from the front, which demonstrates that the proposed algorithm outperforms the conventional RGB-based model.

Advances in Tracking and Recognition of Human Motion

2011 ◽  
pp. 65-71
Author(s):  
Niki Aifanti ◽  
Angel D. Sappa ◽  
Nikos Grammalidis ◽  
Sotiris Grammalidis Malassiotis
Keyword(s):  
Moving Objects ◽  
Research Area ◽  
Initial Position ◽  
Human Motion ◽  
Target Person ◽  
Motion Constraints ◽  
Simplifying Assumptions ◽  
Ill Posed ◽  
Important Research Area ◽  
Tracking And Recognition

Tracking and recognition of human motion has become an important research area in computer vision. In real world conditions it constitutes a complicated problem, considering cluttered backgrounds, gross illumination variations, occlusions, self-occlusions, different clothing and multiple moving objects. These ill-posed problems are usually tackled by making simplifying assumptions regarding the scene or by imposing constraints on the motion. Constraints such as that the contrast between the moving people and the background should be high and that everything in the scene should be static except for the target person are quite often introduced in order to achieve accurate segmentation. Moreover, the motion of the target person is often confined to simple movements with limited occlusions. In addition, assumptions such as known initial position and posture of the person are usually imposed in tracking processes.

A new distributed feature selection technique for classifying gene expression data

2019 ◽  
Vol 12 (04) ◽  
pp. 1950039 ◽  
Author(s):  
Sarah M. Ayyad ◽  
Ahmed I. Saleh ◽  
Labib M. Labib
Keyword(s):  
Gene Expression ◽  
Feature Selection ◽  
Gene Expression Data ◽  
Fuzzy Inference ◽  
Research Area ◽  
Selection Method ◽  
Expression Data ◽  
Feature Selection Technique ◽  
Inference System ◽  
Selection Technique

Classification of gene expression data is a pivotal research area that plays a substantial role in diagnosis and prediction of diseases. Generally, feature selection is one of the extensively used techniques in data mining approaches, especially in classification. Gene expression data are usually composed of dozens of samples characterized by thousands of genes. This increases the dimensionality coupled with the existence of irrelevant and redundant features. Accordingly, the selection of informative genes (features) becomes difficult, which badly affects the gene classification accuracy. In this paper, we consider the feature selection for classifying gene expression microarray datasets. The goal is to detect the most possibly cancer-related genes in a distributed manner, which helps in effectively classifying the samples. Initially, the available huge amount of considered features are subdivided and distributed among several processors. Then, a new filter selection method based on a fuzzy inference system is applied to each subset of the dataset. Finally, all the resulted features are ranked, then a wrapper-based selection method is applied. Experimental results showed that our proposed feature selection technique performs better than other techniques since it produces lower time latency and improves classification performance.

Fuzzy Inference: Its Past and Prospects

2017 ◽  
Vol 21 (1) ◽  
pp. 13-19
Author(s):  
Kiyohiko Uehara ◽  
◽  
Kaoru Hirota ◽  
Keyword(s):  
Fuzzy Inference ◽  
Research Area ◽  
Current Direction ◽  
Future Prospects ◽  
The Past ◽  
The Future ◽  
Inference Methods ◽  
A Current

Fuzzy inference in the past and its future prospects are described to further promote research in the field: First, the basic methods of fuzzy inference are introduced. Then, the progress of fuzzy inference is reviewed, showing its remarkable achievements, especially in industries. A consideration of fuzzy inference is presented from operational viewpoints. It provides a key to creating fuzzy-inference methods in the future. The growing research area of fuzzy inference is also introduced in order to discuss a current direction, reflecting the consideration mentioned above. Moreover, some future prospects on fuzzy inference are presented, which are expected to stimulate research.

Quantum-Inspired Bidirectional Associative Memory for Human–Robot Communication

2014 ◽  
Vol 11 (02) ◽  
pp. 1450006
Author(s):  
Naoki Masuyama ◽  
Chu Kiong Loo ◽  
Naoyuki Kubota
Keyword(s):  
Associative Memory ◽  
Fuzzy Inference ◽  
Learning Algorithm ◽  
Research Area ◽  
Memory Model ◽  
Bidirectional Associative Memory ◽  
Successful Attempt ◽  
Proposed Model ◽  
Theoretical Simulations ◽  
Robot Communication

The emerging research area of a quantum-inspired computing has been applied to various field such as computational intelligence, and showed its superior abilities. However, most existing researches are focused on theoretical simulations, and have not been implemented in systems under practical environment. For human–robot communication, associative memory becomes essential for multi-modal communication. However, it always suffers from low memory capacity and recall reliability. In this paper, we propose a quantum-inspired bidirectional associative memory with fuzzy inference. We show that fuzzy inference satisfies basic postulates of quantum mechanics, but also learning algorithm for weight matrix in associative memory. In addition, we construct a communication system with robot partner using proposed model. This is the first successful attempt to overcome conventional problems in associative memory model with a robot application.

scholarly journals Design of Hybrid Blind Detection Based Spectrum Sensing Technique

2020 ◽  
Vol 12 (4) ◽  
pp. 575-583
Author(s):  
V. Sharma ◽  
S. Joshi
Keyword(s):  
Cognitive Radio ◽  
Spectrum Sensing ◽  
Cooperative Spectrum Sensing ◽  
Primary User ◽  
Research Area ◽  
Detection Accuracy ◽  
Blind Detection ◽  
Spectrum Utilization ◽  
Detection Techniques ◽  
Generation Spectrum

Cognitive Radio is a boon to efficient utilization of spectrum to meet the demand of next generation. Spectrum Sensing (SS) is an active research area, essential to meet the requirement of efficient spectrum utilization as it detects the vacant bands. This paper develops a Hybrid Blind Detection (HBD) technique for cooperative spectrum sensing which combines the Energy Detector (ED) and the Anti-Eigen Value Detection (AVD) techniques together to enhance the detection accuracy of a cognitive radio. Collaboration among the cognitive users is achieved to reduce the error and hard fusion based detection is implemented to detect the existence of primary user. The detection accuracy of the design is evaluated with respect to detection probabilities and the results are examined for improvements with the traditional two stage detection techniques. Fusion rules for the cooperative environment are implemented and compared to detect majority rule suitable for the proposed design.

scholarly journals Mammogram Image Retrieval using Ipso Optimized Anfis Classifier

2019 ◽  
Vol 8 (9S2) ◽  
pp. 799-804
Keyword(s):  
Image Retrieval ◽  
Fuzzy Inference ◽  
Noise Removal ◽  
Research Area ◽  
Query Image ◽  
Inference System ◽  
Neuro Fuzzy ◽  
Input Dataset ◽  
Mammogram Image ◽  
Anfis Classifier

Content-based image retrieval (CBIR) is an research area over the past years that has attracted research. In various medical applications like mammogram analysis CBIR techniques helps the medical team to get similar set of images from a large medical records to help in diagnosis of a disease. This paper proposes an efficient Content-Based Mammogram Image Retrieval method by using an Optimized Classifier. Initially, the input dataset is preprocessed, in which noise removal and contrast enhancement are done. Next, pectoral muscles of the mammogram images are removed using Single Sided Edge Marking (SSEM). Now, feature extraction is done, in which GLCM features, Gabor features and the Local Pattern with Binary features are being removed. The features that are being removed are classified into three classes namely benign, malignant and normal. An optimized classifier named as Adaptive Neuro Fuzzy Inference System (ANFIS), which is optimized by using the Improved Particle Swarm Optimization (IPSO) technique, is used for classification purpose. Finally, similarity is assessed between the trained feature distance vectors and the feature distance vectors of the input query image. Similarity assessment is done using Euclidean Distance metric and the image that has the lowest distance compared with the query is retrieved. The experimental results are obtained for the proposed system and they are compared with the existing techniques.

Depth Illusion by Delayed 3-D Perception (‘Delayed Stereopsis Illusion’): A Novel Way to Determine Computation Times in Human Vision by Depth Reversal in Partially Occluded Moving Objects

Perception ◽  
1996 ◽  
Vol 25 (1_suppl) ◽  
pp. 181-181 ◽  
Author(s):  
R Wolf ◽  
M Schuchardt ◽  
R Rosenzweig
Keyword(s):  
Moving Objects ◽  
Human Vision ◽  
Model Systems ◽  
Depth Information ◽  
Motion Direction ◽  
Processing Times ◽  
Velocity Motion ◽  
Partially Occluded ◽  
Measurable Distance ◽  
Binocular Depth

Viewed through depth-reversing spectacles, nontransparent objects appear to cut ‘gaps’ into a patterned background. In moving objects this gap is seen to extend beyond the occluded area (‘delayed stereopsis illusion’, DSI): Its trailing border appears to lag behind by a precisely measurable distance, indicating a processing time of approximately 0.13 s to accomplish stereopsis [cf Morgan and Castet, 1995 Nature (London)378 380 – 383]. Other than in thigmaesthesia, there is no correction by antedating. Why is this delay not perceived in normal stereopsis? If an object is moving before some background, the background usually maintains its position; it may be occluded, or not. Depth information thus might be extrapolated to the continuously uncovered regions of the patterned background. Depth reversal demands that the occluded region of the background must jump behind the moving, occluding object. As this object is perceived to retain its distance, the background, as it is getting uncovered, must jump back into the foreground, where it can be perceived only after renewed calculation of binocular depth. The dependence of DSI on eye movements, disparity, velocity, motion direction, surface texture, illuminance, spatial frequency, and fractal dimension of the objects involved is currently being investigated in model systems which allow us to determine processing times of human stereopsis under well-defined conditions.

Sign in / Sign up

Export Citation Format

Share Document