Search Results (21)

Building reliable vehicle detection models for intelligent transportation systems calls for large, well-annotated datasets—yet gathering and labelling real traffic data remains both costly and labour-intensive. This paper introduces Traffic Synth, an automated pipeline that generates synthetic training datasets by altering real traffic camera images rather than constructing entirely artificial scenes. The system begins by detecting vehicles through instance segmentation and removing them from the frame. It then places new vehicles directly into the cleared regions using diffusion-based inpainting, all while retaining the original road layout, lighting, and camera perspective. Doing so preserves the realistic scene context while broadening the visual variety of vehicles in the dataset. To ensure that the resulting traffic looks physically plausible, we incorporate a lane-aware prompting mechanism that matches each vehicle’s orientation to the direction of travel as seen from the camera. The system further draws on a weighted vehicle brand database that mirrors the makes and colours commonly found on European roads to better match actual deployment conditions. Class-specific mask processing—involving anisotropic scaling and relative dilation—rounds out the pipeline by improving generation quality across different vehicle size categories. The final output is a set of images with automatically generated annotations in a standard object detection format. Full article

Efficient vehicle classification is essential in intelligent transportation systems, contributing to improved traffic management, road safety, and automated monitoring. However, existing approaches encounter difficulties in real-world scenarios involving overlapping vehicles, varying illumination, and complex backgrounds. We developed a vehicle classification system based on the Segmenting Objects by Locations Version 2 (SOLOv2) instance segmentation framework to achieve accurate identification of seven vehicle classes: sedan, sport utility vehicle, pick-up truck, van, bus, traditional Jeepney, and modern Jeepney. The system employs a Raspberry Pi 5 integrated with an Asus Rog Eye S High Definition Webcam and a 7-inch display, providing an embedded and cost-effective platform for on-site traffic monitoring. A dataset of 2100 annotated images was developed for training and evaluation. The model achieved a mean Intersection over Union of 0.947 and a mean average precision at the intersection of union thresholds from 0.50 to 0.95 of 0.547, with strong performance for bus (a 91.05% average precision (AP)) and modern Jeepney (a 75.03% AP). These results show the technical feasibility and real-world applicability of SOLOv2 for vehicle classification, establishing a robust foundation for integrating advanced computer vision techniques into intelligent transportation systems. Full article

The highway is a crucial component of modern transportation systems, and its efficient management is essential for ensuring safety and facilitating communication. The automatic understanding and reconstruction of highway environments are therefore pivotal for advanced traffic management and intelligent transportation systems. This work introduces a methodology for the fine-grained semantic segmentation and reconstruction of highway environments using dense 3D point cloud data acquired via mobile laser scanning. First, a multi-scale, object-based data augmentation and down-sampling method is introduced to address the issue of training sample imbalance. Subsequently, a deep learning approach utilizing the KPConv convolutional network is proposed to achieve fine-grained semantic segmentation. The segmentation results are then used to reconstruct a 3D model of the highway environment. The methodology is validated on a 32 km stretch of highway, achieving semantic segmentation across 27 categories of environmental features. When evaluated against a manually annotated ground truth, the results exhibit a mean Intersection over Union (mIoU) of 87.27%. These findings demonstrate that the proposed methodology is effective for fine-grained semantic segmentation and instance-level reconstruction of highways in practical scenarios. Full article

Mono RGB cameras and automotive radar sensors provide a complementary information set that makes them excellent candidates for sensor data fusion to obtain robust traffic user detection. This has been widely used in the vehicle domain and recently introduced in roadside-mounted smart infrastructure-based road user detection. However, the performance of the most commonly used late fusion methods often degrades when the camera fails to detect road users in adverse environmental conditions. The solution is to fuse the data using deep neural networks at the early stage of the fusion pipeline to use the complete data provided by both sensors. Research has been carried out in this area, but is limited to vehicle-based sensor setups. Hence, this work proposes a novel deep neural network to jointly fuse RGB mono-camera images and 3D automotive radar point cloud data to obtain enhanced traffic user detection for the roadside-mounted smart infrastructure setup. Projected radar points are first used to generate anchors in image regions with a high likelihood of road users, including areas not visible to the camera. These anchors guide the prediction of 2D bounding boxes, object categories, and confidence scores. Valid detections are then used to segment radar points by instance, and the results are post-processed to produce final road user detections in the ground plane. The trained model is evaluated for different light and weather conditions using ground truth data from a lidar sensor. It provides a precision of 92%, recall of 78%, and F1-score of 85%. The proposed deep fusion methodology has 33%, 6%, and 21% absolute improvement in precision, recall, and F1-score, respectively, compared to object-level spatial fusion output. Full article

Comprehensive datasets are crucial for developing advanced AI solutions in road infrastructure, yet most existing resources focus narrowly on vehicles or a limited set of object categories. To address this gap, we introduce the Korean Road Infrastructure Dataset (KRID), a large-scale dataset designed for real-world road maintenance and safety applications. Our dataset covers highways, national roads, and local roads in both city and non-city areas, comprising 34 distinct types of road infrastructure—from common elements (e.g., traffic signals, gaze-directed poles) to specialized structures (e.g., tunnels, guardrails). Each instance is annotated with either bounding boxes or polygon segmentation masks under stringent quality control and privacy protocols. To demonstrate the utility of this resource, we conducted object detection and segmentation experiments using YOLO-based models, focusing on guardrail damage detection and traffic sign recognition. Preliminary results confirm its suitability for complex, safety-critical scenarios in intelligent transportation systems. Our main contributions include: (1) a broader range of infrastructure classes than conventional “driving perception” datasets, (2) high-resolution, privacy-compliant annotations across diverse road conditions, and (3) open-access availability through AI Hub and GitHub. By highlighting critical yet often overlooked infrastructure elements, this dataset paves the way for AI-driven maintenance workflows, hazard detection, and further innovations in road safety. Full article

Applications such as autonomous driving demand real-time and high-precision instance segmentation to accurately identify and understand objects in an environment, including pedestrians, vehicles, and traffic signs. Ensuring a balance between accuracy and efficiency in instance segmentation systems is critical for such tasks. Traditional convolutional models face limitations in capturing complex features and global context effectively. To address these challenges, we propose an enhanced QueryInst-based instance segmentation framework. First, we replace the traditional CNN backbone with the DaViT Transformer to extract richer, multi-scale features. Next, we integrate Feature Pyramid Network CARAFE to capture global context and recover missed instances. Finally, we incorporate the Complete IoU (CIoU) loss function to optimize object localization and improve prediction accuracy. Experiments on the Cityscapes and COCO datasets demonstrate that our approach achieves mIoU scores of 46.7% and AP score of 45.5%, representing improvements of 6.1% and 2.6% over the baseline, respectively, outperforming other state-of-the-art methods. Full article

The deterioration of physical spaces and changes in the social environment have led to significant challenges and low life satisfaction among residents in post-industrial neighborhoods. While resident satisfaction is closely linked to the built environment, physical attributes alone do not directly influence human feelings. The perception and processing of urban environments, or city images, play a critical mediating role. Previous studies have often explored the impact of either city image perception or physical space attributes on resident satisfaction separately, lacking an integrated approach. This study addresses this gap by examining the interplay between subjective perceptions and objective environmental attributes. Unlike previous studies that use the whole neighborhood area for human perception, our study uses the actual activity ranges of residents to represent the living environment. Utilizing data from Shenyang, China, and employing image semantic segmentation technology and multiple regression methods, we analyze how subjective city image factors influence resident satisfaction and how objective urban spatial indicators affect these perceptions. We integrate these aspects to rank objective spatial indicators by their impact on resident satisfaction. The results demonstrate that all city image factors significantly and positively influence resident satisfaction, with the overall impression of the area’s appearance having the greatest impact (β = 0.362). Certain objective spatial indicators also significantly affect subjective city image perceptions. For instance, traffic lights are negatively correlated with the perception of greenery (β = −0.079), while grass is positively correlated (β = 0.626). Key factors affecting resident satisfaction include pedestrian flow, traffic flow, open spaces, sky openness, and green space levels. This study provides essential insights for urban planners and policymakers, helping prioritize sustainable updates in post-industrial neighborhoods. By guiding targeted revitalization strategies, this research contributes to improving the quality of life and advancing sustainable urban development. Full article

Maritime traffic monitoring systems are particularly important in Mediterranean ports, as they provide more comprehensive data collection compared to traditional systems such as the Automatic Identification System (AIS), which is not mandatory for all vessels. This paper improves the existing real-time maritime traffic monitoring systems by introducing a distance estimation algorithm for monocular cameras, which aims to provide high quality maritime traffic metadata collection for traffic density analysis. Two distance estimation methods based on a pinhole camera model are presented: the Vessel-Focused Distance Estimation (VFDE) and the novel Vessel Object-Focused Distance Estimation (VOFDE). While VFDE uses the predefined height of a vessel for distance estimation, VOFDE uses standardized dimensions of objects on the vessel, detected with a Convolutional Neural Network (CNN) for instance segmentation to enhance estimation accuracy. Our evaluation covers distances up to 414 m, which is significantly beyond the scope of previous studies. When compared to the distances measured with a precise instrument, VOFDE achieves a Percentage Deviation Index (PDI) of 1.34% to 9.45%. This advance holds significant potential for improving maritime surveillance with monocular cameras and is also applicable in other areas, such as low-cost maritime vehicles equipped with single cameras. Full article

With the rapid development of the autonomous driving industry, there is increasing research on related perception tasks. However, research on road surface traffic sign detection tasks is still limited. There are two main challenges to this task. First, when the target object’s pixel ratio is small, the detection accuracy often decreases. Second, the existing publicly available road surface traffic sign datasets have limited image data. To address these issues, this paper proposes a new instance segmentation network, RTS R-CNN, for road surface traffic sign detection tasks based on Mask R-CNN. The network can accurately perceive road surface traffic signs and provide important information for the autonomous driving decision-making system. Specifically, CSPDarkNet53_ECA is proposed in the feature extraction stage to enhance the performance of deep convolutional networks by increasing inter-channel interactions. Second, to improve the network’s detection accuracy for small target objects, GR-PAFPN is proposed in the feature fusion part, which uses a residual feature enhancement module (RFA) and atrous spatial pyramid pooling (ASPP) to optimize PAFPN and introduces a balanced feature pyramid module (BFP) to handle the imbalanced feature information at different resolutions. Finally, data augmentation is used to generate more data and prevent overfitting in specific scenarios. The proposed method has been tested on the open-source dataset Ceymo, achieving a Macro F₁-score of 87.56%, which is 2.3% higher than the baseline method, while the inference speed reaches 23.5 FPS. Full article

As autonomous driving is quickly becoming a reality, the most considerable challenge with self-driving remains safety, as the car must process surroundings to make the correct predictions. This paper explores the detection and classification of moving objects, such as vehicles and pedestrians, on a pixel level. Using the CARLA simulator, we collected data from a single front-facing camera, thus excluding standard sensor technologies like lidar or radar. This research aims to test the generalization capabilities of models trained using front-camera images on inputs from differently positioned cameras capturing 360 surroundings. We tackle the described challenge with the task of instance segmentation using the most famous instance segmentation algorithms: Mask Region-based Convolutional Neural Network and YOLOv7. We show to what extent a monocular setup can be used for the instance segmentation of the perspectives that differ from the baseline captured by the front camera. Full article

Point cloud registration plays a crucial role in 3D mapping and localization. Urban scene point clouds pose significant challenges for registration due to their large data volume, similar scenarios, and dynamic objects. Estimating the location by instances (bulidings, traffic lights, etc.) in urban scenes is a more humanized matter. In this paper, we propose PCRMLP (point cloud registration MLP), a novel model for urban scene point cloud registration that achieves comparable registration performance to prior learning-based methods. Compared to previous works that focused on extracting features and estimating correspondence, PCRMLP estimates transformation implicitly from concrete instances. The key innovation lies in the instance-level urban scene representation method, which leverages semantic segmentation and density-based spatial clustering of applications with noise (DBSCAN) to generate instance descriptors, enabling robust feature extraction, dynamic object filtering, and logical transformation estimation. Then, a lightweight network consisting of Multilayer Perceptrons (MLPs) is employed to obtain transformation in an encoder–decoder manner. Experimental validation on the KITTI dataset demonstrates that PCRMLP achieves satisfactory coarse transformation estimates from instance descriptors within a remarkable time of 0.0028 s. With the incorporation of an ICP refinement module, our proposed method outperforms prior learning-based approaches, yielding a rotation error of 2.01° and a translation error of 1.58 m. The experimental results highlight PCRMLP’s potential for coarse registration of urban scene point clouds, thereby paving the way for its application in instance-level semantic mapping and localization. Full article

There are known limitations in mobile omnidirectional camera systems with an equirectangular projection in the wild, such as momentum-caused object distortion within images, partial occlusion and the effects of environmental settings. The localization, instance segmentation and classification of traffic signs from image data is of significant importance to applications such as Traffic Sign Detection and Recognition (TSDR) and Advanced Driver Assistance Systems (ADAS). Works show the efficacy of using state-of-the-art deep pixel-wise methods for this task yet rely on the input of classical landscape image data, automatic camera focus and collection in ideal weather settings, which does not accurately represent the application of technologies in the wild. We present a new processing pipeline for extracting objects within omnidirectional images in the wild, with included demonstration in a Traffic Sign Detection and Recognition (TDSR) system. We compare Mask RCNN, Cascade RCNN, and Hybrid Task Cascade (HTC) methods, while testing RsNeXt 101, Swin-S and HRNetV2p backbones, with transfer learning for localization and instance segmentation. The results from our multinomial classification experiment show that using our proposed pipeline, given that a traffic sign is detected, there is above a 95% chance that it is classified correctly between 12 classes despite the limitations mentioned. Our results on the projected images should provide a path to use omnidirectional images with image processing to enable the full surrounding awareness from one image source. Full article

Detecting the objects surrounding a moving vehicle is essential for autonomous driving and for any kind of advanced driving assistance system; such a system can also be used for analyzing the surrounding traffic as the vehicle moves. The most popular techniques for object detection are based on image processing; in recent years, they have become increasingly focused on artificial intelligence. Systems using monocular vision are increasingly popular for driving assistance, as they do not require complex calibration and setup. The lack of three-dimensional data is compensated for by the efficient and accurate classification of the input image pixels. The detected objects are usually identified as cuboids in the 3D space, or as rectangles in the image space. Recently, instance segmentation techniques have been developed that are able to identify the freeform set of pixels that form an individual object, using complex convolutional neural networks (CNNs). This paper presents an alternative to these instance segmentation networks, combining much simpler semantic segmentation networks with light, geometrical post-processing techniques, to achieve instance segmentation results. The semantic segmentation network produces four semantic labels that identify the quarters of the individual objects: top left, top right, bottom left, and bottom right. These pixels are grouped into connected regions, based on their proximity and their position with respect to the whole object. Each quarter is used to generate a complete object hypothesis, which is then scored according to object pixel fitness. The individual homogeneous regions extracted from the labeled pixels are then assigned to the best-fitted rectangles, leading to complete and freeform identification of the pixels of individual objects. The accuracy is similar to instance segmentation-based methods but with reduced complexity in terms of trainable parameters, which leads to a reduced demand for computational resources. Full article

High-resolution traffic data, comprising trajectories of individual road users, are of great importance to the development of Intelligent Transportation Systems (ITS), in which they can be used for traffic microsimulations and applications such as connected vehicles. Roadside laser scanning systems are increasingly being used for tracking on-road objects, for which tracking-by-detection is the widely acknowledged method; however, this method is sensitive to misdetections, resulting in shortened and discontinuous object trajectories. To address this, a Joint Detection And Tracking (JDAT) scheme, which runs detection and tracking in parallel, is proposed to mitigate miss-detections at the vehicle detection stage. Road users are first separated by moving point semantic segmentation and then instance clustering. Afterwards, two procedures, object detection and object tracking, are conducted in parallel. In object detection, PointVoxel-RCNN (PV-RCNN) is employed to detect vehicles and pedestrians from the extracted moving points. In object tracking, a tracker utilizing the Unscented Kalman Filter (UKF) and Joint Probabilistic Data Association Filter (JPDAF) is used to obtain the trajectories of all moving objects. The identities of the trajectories are determined from the results of object detection by using only a certain number of representatives for each trajectory. The developed scheme has been validated at three urban study sites using two different lidar sensors. Compared with a tracking-by-detection method, the average range of object trajectories has been increased by >20%. The approach can also successfully maintain continuity of the trajectories by bridging gaps caused by miss-detections. Full article

Bottom-up saliency models identify the salient regions of an image based on features such as color, intensity and orientation. These models are typically used as predictors of human visual behavior and for computer vision tasks. In this paper, we conduct a systematic evaluation of the saliency maps computed with four selected bottom-up models on images of urban and highway traffic scenes. Saliency both over whole images and on object level is investigated and elaborated in terms of the energy and the entropy of the saliency maps. We identify significant differences with respect to the amount, size and shape-complexity of the salient areas computed by different models. Based on these findings, we analyze the likelihood that object instances fall within the salient areas of an image and investigate the agreement between the segments of traffic participants and the saliency maps of the different models. The overall and object-level analysis provides insights on the distinctive features of salient areas identified by different models, which can be used as selection criteria for prospective applications in autonomous driving such as object detection and tracking. Full article