Morteza Rahbar

Bio: Morteza Rahbar is an academic researcher from Iran University of Science and Technology. The author has contributed to research in topics: Daylight & Process (computing). The author has an hindex of 3, co-authored 9 publications receiving 57 citations. Previous affiliations of Morteza Rahbar include Tarbiat Modares University & ETH Zurich.

DublinCity: Annotated LiDAR Point Cloud and its Applications

Abstract: Scene understanding of full-scale 3D models of an urban area remains a challenging task. While advanced computer vision techniques offer cost-effective approaches to analyse 3D urban elements, a precise and densely labelled dataset is quintessential. The paper presents the first-ever labelled dataset for a highly dense Aerial Laser Scanning (ALS) point cloud at city-scale. This work introduces a novel benchmark dataset that includes a manually annotated point cloud for over 260 million laser scanning points into 100'000 (approx.) assets from Dublin LiDAR point cloud [12] in 2015. Objects are labelled into 13 classes using hierarchical levels of detail from large (i.e., building, vegetation and ground) to refined (i.e., window, door and tree) elements. To validate the performance of our dataset, two different applications are showcased. Firstly, the labelled point cloud is employed for training Convolutional Neural Networks (CNNs) to classify urban elements. The dataset is tested on the well-known state-of-the-art CNNs (i.e., PointNet, PointNet++ and So-Net). Secondly, the complete ALS dataset is applied as detailed ground truth for city-scale image-based 3D reconstruction.

DublinCity: Annotated LiDAR Point Cloud and its Applications

Abstract: Scene understanding of full-scale 3D models of an urban area remains a challenging task. While advanced computer vision techniques offer cost-effective approaches to analyse 3D urban elements, a precise and densely labelled dataset is quintessential. The paper presents the first-ever labelled dataset for a highly dense Aerial Laser Scanning (ALS) point cloud at city-scale. This work introduces a novel benchmark dataset that includes a manually annotated point cloud for over 260 million laser scanning points into 100'000 (approx.) assets from Dublin LiDAR point cloud [12] in 2015. Objects are labelled into 13 classes using hierarchical levels of detail from large (i.e., building, vegetation and ground) to refined (i.e., window, door and tree) elements. To validate the performance of our dataset, two different applications are showcased. Firstly, the labelled point cloud is employed for training Convolutional Neural Networks (CNNs) to classify urban elements. The dataset is tested on the well-known state-of-the-art CNNs (i.e., PointNet, PointNet++ and So-Net). Secondly, the complete ALS dataset is applied as detailed ground truth for city-scale image-based 3D reconstruction.

Architectural layout design through deep learning and agent-based modeling: A hybrid approach

Abstract: This paper presents a novel hybrid approach for generating automated 2D architectural layouts by combining agent-based modeling with deep learning algorithms. The primary goal of this research is to maintain the designers' high-level, supervisory control over the generated results and process, allowing them to manage the whole process so that the created results satisfy the desired topological and geometrical constraints. The proposed hybrid approach consists of two different methods. First, hierarchical phases of agent-based modeling are simulated to generate a bubble diagram that satisfies the topological conditions. A rule-based algorithm converts bubble diagrams into heat maps. Second, the pix2pix algorithm translates the heat maps into an architectural spatial layout as a conditional GAN and deep learning approach. In doing so, a unique dataset was manually generated, and the cGAN algorithm was trained based on this dataset. The hybrid method of these processes makes it possible to generate an architectural layout based on a particular footprint and desired high-level constraints. The findings of agent-based modeling showed complete consistency with the required topological requirements, whereas deep learning results demonstrated the ability of cGAN to satisfy geometrical constraints learned throughout the training phase. The hybrid method's results showed enhanced computational accuracy in generating synthetic architectural layouts compared to previous studies.

Generating Synthetic Space Allocation Probability Layouts Based on Trained Conditional-GANs

Abstract: In this paper, a data-driven generative method is applied to generate synthetic space allocation probability layout. This generated layout could be helpful in the early stage of an architectural de...

Computing Systems for Autonomous Driving: State-of-the-Art and Challenges

Abstract: The recent proliferation of computing technologies (e.g., sensors, computer vision, machine learning, and hardware acceleration), and the broad deployment of communication mechanisms (e.g., DSRC, C-V2X, 5G) have pushed the horizon of autonomous driving, which automates the decision and control of vehicles by leveraging the perception results based on multiple sensors. The key to the success of these autonomous systems is making a reliable decision in real-time fashion. However, accidents and fatalities caused by early deployed autonomous vehicles arise from time to time. The real traffic environment is too complicated for current autonomous driving computing systems to understand and handle. In this paper, we present state-of-the-art computing systems for autonomous driving, including seven performance metrics and nine key technologies, followed by twelve challenges to realize autonomous driving. We hope this paper will gain attention from both the computing and automotive communities and inspire more research in this direction.

Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challenges

Abstract: An essential prerequisite for unleashing the potential of supervised deep learning algorithms in the area of 3D scene understanding is the availability of large-scale and richly annotated datasets. However, publicly available datasets are either in relative small spatial scales or have limited semantic annotations due to the expensive cost of data acquisition and data annotation, which severely limits the development of fine-grained semantic understanding in the context of 3D point clouds. In this paper, we present an urban-scale photogrammetric point cloud dataset with nearly three billion richly annotated points, which is three times the number of labeled points than the existing largest photogrammetric point cloud dataset. Our dataset consists of large areas from three UK cities, covering about 7.6 km^2 of the city landscape. In the dataset, each 3D point is labeled as one of 13 semantic classes. We extensively evaluate the performance of state-of-the-art algorithms on our dataset and provide a comprehensive analysis of the results. In particular, we identify several key challenges towards urban-scale point cloud understanding. The dataset is available at this https URL.