Mohamed A. Abdelwahab

Mohamed A. Abdelwahab

Auto-generated profile, based on publicly available information

Mohamed A. Abdelwahab

Center of Coevolutionary Research for Sustainable Communities, Kyushu University, Fukuoka, Japan

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 February 2019
Verified
Conference Paper
Closed access
MAMohamed A. Abdelwahab
Mohamed A. Abdelwahab
Vehicle counting is considered one of the most important applications in traffic control and management. To count vehicles, synchronous vehicle detection and tracking should be carried out. Recently, detection via deep neural networks (DNN) has achieved good performance. However, exploiting the DNN efficiently for vehicle counting is still challenging. In this paper, an efficient approach for vehicle counting employing DNN and KLT tracker is proposed. To decrease the time complexity, vehicles are detected via DNN every N-frames, N=15 for example. Trajectories are extracted by tracking corner points through the N-frames. Then an efficient algorithm is introduced to assign unique vehicle labels to their corresponding trajectories. The proposed results, performed on diverse vehicle videos, show that vehicles are accurately tracked and counted whatever they are detected one or more times by the DNN.

1 January 2019 in Electronics Letters
Verified
Journal Article
Open access
PDF file
MAM.A. Abdelwahab
M.A. Abdelwahab
Systems for counting vehicles should be fast enough to be implemented in real‐time situations. Most of the related work uses two stages for vehicle counting, vehicle detection and tracking, which increase the computational complexity. In this Letter, a fast and efficient approach for vehicle counting is proposed, where there is no need for the vehicle tracking step. A background model is created only for a narrow region, a line, in the video frames. The moving vehicles are detected as foreground objects while passing this narrow region. Morphological processes are applied to the extracted objects to enhance them and decrease the effects of vehicle occlusions. Finally, an efficient counting vehicles method is introduced employing only the extracted detection information. The experimental results performed on diverse videos show that the proposed method is fast and accurate. The average execution time per frame is 7.78 ms.

1 January 2020 in IEEE Access
Verified
Journal Article
Open access
MAMohamed A. Abdelwahab
Mohamed A. Abdelwahab
Mohamed Abdel-NasserMohamed Abdel-Nasser
Mohamed Abdel-Nasser
MHMaiya Hori
Maiya Hori
Traffic congestion detection systems help manage traffic in crowded cities by analyzing videos of vehicles. Existing systems largely depend on texture and motion features. Such systems face several challenges, including illumination changes caused by variations in weather conditions, complexity of scenes, vehicle occlusion, and the ambiguity of stopped vehicles. To overcome these issues, this article proposes a rapid and reliable traffic congestion detection method based on the modeling of video dynamics using deep residual learning and motion trajectories. The proposed method efficiently uses both motion and deep texture features to overcome the limitations of existing methods. Unlike other methods that simply extract texture features from a single frame, we use an efficient representation learning method to capture the latent structures in traffic videos by modeling the evolution of texture features. This representation yields a noticeable improvement in detection results under various weather conditions. Regarding motion features, we propose an algorithm to distinguish stopped vehicles and background objects, whereas most existing motion-based approaches fail to address this issue. Both types of obtained features are used to construct an ensemble classification model based on the support vector machine algorithm. Two benchmark datasets are considered to demonstrate the robustness of the proposed method: the UCSD dataset and NU1 video dataset. The proposed method achieves competitive results (97.64% accuracy) when compared to state-of-the-art methods.

1 February 2020
Verified
Conference Paper
Closed access
ZAZaynab Al-Ariny
Zaynab Al-Ariny
MAMohamed A. Abdelwahab
Mohamed A. Abdelwahab
MFMahmoud Fakhry
Mahmoud Fakhry
EHEl-Sayed Hasaneen
El-Sayed Hasaneen
In this paper, an accurate approach for vehicle counting in videos using Mask R-CNN and KLT tracker is proposed. Vehicle detection is performed for each N frames using Mask R-CNN instance segmentation model. This model outperforms other deep learning models that using bounding box detection as it provides a segmentation mask for each detected object, the outperformance comes up clearly in cases of occlusions. Once the objects are detected, their corner points are extracted and tracked. An efficient method is introduced to assign point trajectories to their corresponding detected vehicles. The proposed counting algorithm distinguishes precisely between the new vehicles and the counted ones. The experiments performed on diverse challenging videos show excellent results compared to state-of-the-art counting methods.

3 May 2018 in International Journal of Remote Sensing
Verified
Journal Article
Closed access
YMYasser Mostafa
Yasser Mostafa
MAMohamed A. Abdelwahab
Mohamed A. Abdelwahab
High spatial resolution images available by satellites such as Ikonos, Quickbird, and WorldView-2 provide more information for remote sensing applications, such as object detection, classification, change detection, and object mapping. The presence of shadow reduces the amount of information that can be extracted and consequently makes these applications more difficult or even impossible. In this article, a shadow restoration approach for high-resolution satellite images is proposed. The approach detects the shadow area and segments the image into regions according to the land surface type. Then, shadow restoration is carried out for each region based on the degree of correspondence between shadow and neighbouring non-shadow regions. The proposed approach is applied to study areas from Ikonos and WorldView-2 satellite images. A comparison to the standard approaches for shadow restoration is performed, and an accuracy assessment is carried out by visual inspection and land-cover classification. The results show that the enhanced shadow regions using the proposed approach have better appearances and are highly compatible with their surrounding non-shadow regions. In addition, the overall accuracy is higher than those of the standard approaches.

1 December 2015
Verified
Conference Paper
Closed access
MAMohamed A. Abdelwahab
Mohamed A. Abdelwahab
MAMoataz M. Abdelwahab
Moataz M. Abdelwahab
Real time detection and tracking of multi vehicles in airborne videos is still a challenging problem due to the camera motion and low resolution. In this paper, a real time technique for simultaneously detecting, tracking and counting vehicles in airborne and stationary camera videos is proposed. First, feature points are extracted and tracked through video frames. A new strategy is used for removing the non-stationary background points by measuring the changes in the histogram of the pixels around each feature point with time. The obtained foreground features are clustered and grouped into separate trackable vehicles based on their motion properties. Experimental results performed on videos representing airborne and fixed cameras confirm the excellent properties of the proposed algorithm.