Huy Hung Nguyen

Ho Chi Minh City International University | HCMIU · School of Computer Science and Engineering

Traffic flow estimation is an essential task in modern intelligent transportation systems. Many types of information, including vehicle type, vehicle totals, and movement direction, are vital for mitigating transportation-related tasks and effective traffic control strategies. With the development of embedded devices, systems can process captured v...

This technical report presents an overview of our method for Object Detection in the Hazy Condition in the 5 th UG2+ Challenge at CVPR 2022. Based on the detailed analysis of the dataset, a dehazing model with half instance normalization is used to enhance the visibility of objects in hazy images slightly. Then different object detection models are...

Advanced Driver Assistance Systems (ADAS) are a collection of intelligent solutions integrated into next-generation vehicles to assist in safe driving. When building ADAS systems, the main goals are that they are stable, flexible, easy to maintain, and allow for error tracing. If a driving assistance algorithm is designed to be implemented on one m...

Rectification is a core programming process that involves multiple views. In this study, we focus on uncalibrated cases that neglect intrinsic and extrinsic camera information. Existing uncalibrated rectification methods use feature-matching techniques to form relationships between different views and use those features to estimate optimized homogr...

In intelligent traffic systems, vehicle detection and counting have become an important task. The counting information is essential for reducing traffic congestion and improving traffic signal capability. Traditional methods have been focusing on counting vehicles in a single frame or consecutive frames. However, they have not yet considered the mo...

Many successful deep learning networks for object detection have been proposed in recent years, but direct comparison is difficult due to different resolutions, training validation data, and frameworks used to train these networks. In particular, we use DRIVE PX2 as a reference computing platform, which is manufactured by NVIDIA Corporation for dev...

Lane detection is a well-research area of computer vision with applications in intelligent traffic monitoring systems and autonomous driver assisting system. In traffic monitoring system, lane detection is one of the key components as it provides a backbone for supporting main functions of the system including vehicle detection and classification,...

Optical flow is the pattern that represents the motion of objects, edges, surfaces in real world by using displacement vectors or color flow. Application of optical flow is used in various problems, especially in traffic monitoring system. The result of optical flow estimation can be used for traffic control, anomaly event detection, vehicle tracki...

Optical flow is the pattern that represents the motion of objects, edges, surfaces in real world by using displacement vectors or color flow. Application of optical flow is used in variant problems, especially in traffic monitoring system. The result of optical flow estimation can be used for traffic control, anomaly events detection, vehicle track...