محمد عبد علي حسين جريو

Event cameras provide microsecond temporal resolution, high dynamic range, and low latency by asynchronously capturing per-pixel luminance changes, thereby introducing a novel sensing paradigm. These advantages render them well-suited for high-speed applications such as autonomous vehicles and dynamic environments. Nevertheless, the sparsity of event data and the absence of dense annotations are significant obstacles to supervised learning for motion segmentation from event streams. Domain adaptation is also challenging due to the considerable domain shift in intensity images. To address these challenges, we propose a two-phase cross-modality adaptation framework that translates motion segmentation knowledge from labeled RGB-flow data to unlabeled event streams. A dual-branch encoder extracts modality-specific motion and appearance features from RGB and optical flow in the source domain. Using reconstruction networks, event voxel grids are converted into pseudo-image and pseudo-flow modalities in the target domain. These modalities are subsequently re-encoded using frozen RGB-trained encoders. Multi-level consistency losses are implemented on features, predictions, and outputs to enforce domain alignment. Our design enables the model to acquire domain-invariant, semantically rich features through the use of shallow architectures, thereby reducing training costs and facilitating real-time inference with a lightweight prediction path. The proposed architecture, alongside the utilized hybrid loss function, effectively bridges the domain and modality gap. We evaluate our method on two challenging benchmarks: EVIMO2, which incorporates real-world dynamics, high-speed motion, illumination variation, and multiple independently moving objects; and MOD++, which features complex object dynamics, collisions, and dense 1kHz supervision in synthetic scenes. The proposed UDA framework achieves 83.1% and 79.4% accuracy on EVIMO2 and MOD++, respectively, outperforming existing state-of-the-art approaches, such as EV-Transfer and SHOT, by up to 3.6%. Additionally, it is lighter and faster and also delivers enhanced mIoU and F1 Score.

Propose Troubling countries one after another, the COVID-19 pandemic has dramatically affected the health and well-being of the world’s population. The disease may continue to persist more extensively due to the increasing number of new cases daily, the rapid spread of the virus, and delay in the PCR analysis results. Therefore, it is necessary to consider developing assistive methods for detecting and diagnosing the COVID-19 to eradicate the spread of the novel coronavirus among people. Based on convolutional neural networks (CNNs), automated detection systems have shown promising results of diagnosing patients with the COVID-19 through radiography; thus, they are introduced as a workable solution to the COVID-19 diagnosis. Materials and methods Based on the enhancement of the classical visual geometry group (VGG) network with the convolutional COVID block (CCBlock), an efficient screening model was proposed in this study to diagnose and distinguish patients with the COVID-19 from those with pneumonia and the healthy people through radiography. The model testing dataset included 1828 X-ray images available on public platforms. Three hundred and ten images were showing confirmed COVID-19 cases, 864 images indicating pneumonia cases, and 654 images showing healthy people. Results According to the test results, enhancing the classical VGG network with radiography provided the highest diagnosis performance and overall accuracy of 98.52% for two classes as well as accuracy of 95.34% for three classes. Conclusions According to the results, using the enhanced VGG deep neural network can help radiologists automatically diagnose the COVID-19 through radiography.

Human activity remains a challenge in a number of applications such as HMI, automatic surveillance, face analysis, ID systems, etc. Face detection and tracking therefore makes a key part in these applications. Without a reliable face detection system machine vision projects will face failure. Owing to rapid development of processors, precission of algorithms are a key aspect in their efficiency. In this research we have developed an efficeint system to detect an dtrach faces in a video sequence by smart modification in current available algorithms. Applying a suitable set of properties which stem from natural face properties has enabled us to present a reliable fusion between detection and tracking of face in frames of a video sequence. The detection method in this work is based on Viola Jones algorithm followed by KLT algorithm as a tracker. We have shown that, when applied to differenet sequences, results are satisfactory.

زار وفد من مديرية التخطيط والتنمية الاقليمية في محافظة النجف الاشرف برئاسة المهندس مهند طاهر كلية التخطيط العمراني للاطلاع على اعمال طلبة الماجستير في قسم التخطيط الحضري والاطلاع على تقديم المرحلة الثانية (مرحلة تحليل البيانات) الخاص بالتخطيط والتصميم الحضري لقرية الدسم والتي تنطوي تحت متطلبات مادة التخطيط والتصميم الحضري المستدام للقطاعات الخضراء والخاصة ببرنامج الماجستير في تخطيط المدن المستدامة في قسم التخطيط الحضري. يذكر ان هذا النشاط يأتي ضمن إطار التعاون بين كليتنا ومديرية التخطيط والتنمية الاقليمية في النجف الاشرف.