Hamd Ait Abdelali

Bio: Hamd Ait Abdelali is an academic researcher from Mohammed V University. The author has contributed to research in topics: Video tracking & Histogram. The author has an hindex of 4, co-authored 6 publications receiving 40 citations.

An Adaptive Object Tracking Using Kalman Filter and Probability Product Kernel

Abstract: We present a new method for object tracking; we use an efficient local search scheme based on the Kalman filter and the probability product kernel KFPPK to find the image region with a histogram most similar to the histogram of the tracked target. Experimental results verify the effectiveness of this proposed system.

Algorithm for moving object detection and tracking in video sequence using color feature

Abstract: In this paper we present an algorithm research on moving object detection and tracking in video sequence using color feature In this algorithm we combine between the probability product kernels as a similarity measure, and the integral image to compute the histograms of all possible target regions of object tracking in data sequence The objective of this algorithm is to associate target object in consecutive video frames The association can be especially difficult when the objects are moving fast relative to the frame rate Another situation that increases the complexity of the problem is when the tracked object changes orientation over time For these situations the proposed algorithm is used to improve the tracking accuracy and decrease the tracking failures in the video tracking process, and usually employ a motion model which describes how the image of the target might change for different possible motions of the object

A new moving object tracking method using particle filter and probability product kernel

Abstract: Moving object tracking is a tricky job in computer vision problems. In this approach, the object tracking system relies on the deterministic search of target, whose color content matches a reference histogram model. A simple RGB histogram-based color model is used to develop our observation system. Secondly and finally, we describe a new approach for moving object tracking with particle filter by shape information. Particle filtering has been proven very successful for non-Gaussian and non-linear estimation problems. In this approach we combine between particle filter and the probability product kernels as a similarity measure using integral image to compute the histograms of all possible target regions of object tracking in video sequence. The shape similarity between a target and estimated regions in the video sequence is measured by their normalized histogram. Target of object tracking is created instantly by selecting an object from the video sequence by a rectangle. Experimental results have been presented to show the effectiveness of our proposed system.

Object tracking in video via particle filter

Abstract: In this paper, we present a new method for object tracking. We use an efficient local search scheme based on the probability product kernel using particle filter PPKPF to find the image region with a histogram most similar to the histogram of the tracked target. Experimental results verify the effectiveness of this proposed algorithm.

Multi-object Detection and Tracking (MODT) Machine Learning Model for Real-Time Video Surveillance Systems

Abstract: Recently, video surveillance has garnered considerable attention in various real-time applications. Due to advances in the field of machine learning, numerous techniques have been developed for multi-object detection and tracking (MODT). This paper introduces a new MODT methodology. The proposed method uses an optimal Kalman filtering technique to track the moving objects in video frames. The video clips were converted based on the number of frames into morphological operations using the region growing model. After distinguishing the objects, Kalman filtering was applied for parameter optimization using the probability-based grasshopper algorithm. Using the optimal parameters, the selected objects were tracked in each frame by a similarity measure. Finally, the proposed MODT framework was executed, and the results were assessed. The experiments showed that the MODT framework achieved maximum detection and tracking accuracies of 76.23% and 86.78%, respectively. The results achieved with Kalman filtering in the MODT process are compared with the results of previous studies.

Environmental monitoring as an IoT application in building smart campus of Universitas Udayana

Abstract: The idea of Internet of Things as a platform in smart campus has become increasingly popular. It requires an infrastructure comprised of communication networks, sensor nodes, and gateways to connect to the Internet. Each sensor node is responsible to collect data from the surrounding environment. This paper designs a wireless sensor network in internet of thing for environmental monitoring application. There are two scenarios design for this project. One uses EPS8266 to send data directly to the internet, and the other is to use Arduino and XBee 802.15.4 in multi hop wireless network. In the latter, data from several nodes are collected by an aggregator and send them to the gateway. The wireless communication between the nodes and aggregator is based on XBee 802.15.4 Radio. The XBee radios that connected to the nodes will act as a router, while another one that connected to the gateway act as coordinator. Arduino Wi-Fi shield with 802.11 standard is used to send the information to a web server. A web server based on Webrick with Ruby on Rails platform is built to display the measurement results.

Preliminary study on angiosperm genus classification by weight decay and combination of most abundant color index with fractional Fourier entropy

Abstract: In order to develop an efficient angiosperm-genus classification system, we first collected petal image of Hibiscus, Orchis, and Prunus, by digital camera, and remove the backgrounds by region-growing method. Next, we proposed a novel feature-extraction method, which combined most abundant color index (MACI) and introduced the fractional Fourier entropy (FRFE). Third, we submitted the 41 features to a single-hidden layer feedforward neural-network (SLFN), with weight decay (WD) to avoid overfitting. The 10 × 10-fold cross validation showed our method achieved an overall accuracy of 98.92%. Without weight decay, the overall accuracy decreased to 95.50%. Our experiments validated that optimal decay factor is 0.1, and optimal number of hidden neurons is 15. This proposed method is excellent. It performs better than six state-of-the-art approaches and AlexNet. The weight decay helps to enhance generalization of our classifier.

An Adaptive Object Tracking Using Kalman Filter and Probability Product Kernel

Abstract: We present a new method for object tracking; we use an efficient local search scheme based on the Kalman filter and the probability product kernel KFPPK to find the image region with a histogram most similar to the histogram of the tracked target. Experimental results verify the effectiveness of this proposed system.