E Egor Bondarev

Modelling of input-parameter dependency for performance predictions of component-based embedded systems

The guaranty of meeting the timing constraints during the design phase of real-time component-based embedded software has not been realized. To satisfy real-time requirements, we need to understand behaviour and resource usage of a system over time. In this paper, we address both aspects in detail by observing the influence of input data on the system behaviour and performance. We extend an existing scenario simulation approach that features the modelling of input parameter dependencies and simulating the execution of the models. The approach enables specification of the dependencies in the component models, as well as initialisation of the parameters in the application scenario model. This gives a component-based application designer an explorative possibility of going through all possible execution scenarios with different parameter initialisations, and finding the worst-case scenarios where the predicted performance does not satisfy the requirements. The identification of these scenarios is important because it avoids system redesign at the later stage. In addition, the conditional behaviour and resource usage modelling with respect to the input data provide more accurate prediction.

Compositional Performance Analysis of Component-Based Systems on Heterogeneous Multiprocessor Platforms

This paper presents a compositional performance analysis technique, enabling predictable deployment of software components on heterogeneous multiprocessor architectures. This analysis technique introduces (a) composable software and hardware component models representing abstract specification of the component behaviour and corresponding resources, (b) operational semantics enabling composition of the models into an executable system model, and (c) simulation-based analysis of the obtained executable model resulting in predicted performance attributes. Example attributes are response time, throughput, utilization of processors, memory and communication lines. Special attention is paid to modeling of both passive and active components exploiting synchronous method invocation and asynchronous message passing interaction. We made an experimental validation of the above framework for two case studies: an MPEG-4 decoder and a car navigation system. It was found that the prediction error on task latencies and processor usage was within 10%

Incremental and batch planar simplification of dense point cloud maps

Dense RGB-D SLAM techniques and high-fidelity LIDAR scanners are examples from an abundant set of systems capable of providing multi-million point datasets. These datasets quickly become difficult to process due to the sheer volume of data, typically containing significant redundant information, such as the representation of planar surfaces with millions of points. In order to exploit the richness of information provided by dense methods in real-time robotics, techniques are required to reduce the inherent redundancy of the data. In this paper we present a method for incremental planar segmentation of a gradually expanding point cloud map and a method for efficient triangulation and texturing of planar surface segments. Experimental results show that our incremental segmentation method is capable of running in real-time while producing a segmentation faithful to what would be achieved using a batch segmentation method. Our results also show that the proposed planar simplification and triangulation algorithm removes more than 90% of the input planar points, leading to a triangulation with only 10% of the original quantity of triangles per planar segment. Additionally, our texture generation algorithm preserves all colour information contained within planar segments, resulting in a visually appealing and geometrically accurate simplified representation. Online incremental planar segmentation algorithm capable of running in real-time.Point cloud plane segment triangulation that preserves principle geometric features.Texture generation algorithm that maintains visual appearance of planar surfaces.

Performance-efficient architecture for free-viewpoint 3DTV receiver

This paper presents algorithmic and architectural solutions for a free-viewpoint 3DTV receiver system. We describe our rendering algorithm and evaluate performance-related challenges in mapping of the algorithm on a receiver board of which the architecture is outlined. It is found that the required processing load exceeds the provisioning of dual Virtex5 FPGAs. We develop several mapping optimizations to fit the rendering algorithm into a platform.

A process for resolving performance trade-offs in component-based architectures

Designing architectures requires the balancing of multiple system quality objectives. In this paper, we present techniques that support the exploration of the quality properties of component-based architectures deployed on multiprocessor platforms. Special attention is paid to real-time properties and efficiency of resource use. The main steps of the process are (1) a simple way of modelling properties of software and hardware components, (2) from the component properties, a model of an execution architecture is composed and analyzed for system-level quality attributes, (3) for the composed system, selected execution scenarios are evaluated, (4) Pareto curves are used for making design trade-offs explicit. The process has been applied to several industrial systems. A Car Radio Navigation system is used to illustrate the method. For this system, we consider architectural alternatives, show their specification, and present their trade-off with respect to cost, performance and robustness.

Planar simplification and texturing of dense point cloud maps

Dense RGB-D based SLAM techniques and high-fidelity LIDAR scanners are examples from an abundant set of systems capable of providing multi-million point datasets. These large datasets quickly become difficult to process and work with due to the sheer volume of data, which typically contains significant redundant information, such as the representation of planar surfaces with hundreds of thousands of points. In order to exploit the richness of information provided by dense methods in real-time robotics, techniques are required to reduce the inherent redundancy of the data. In this paper we present a method for efficient triangulation and texturing of planar surfaces in large point clouds. Experimental results show that our algorithm removes more than 90% of the input planar points, leading to a triangulation with only 10% of the original amount of triangles per planar segment, improving upon an existing planar simplification algorithm. Despite the large reduction in vertex count, the principal geometric features of each segment are well preserved. In addition to this, our texture generation algorithm preserves all colour information contained within planar segments, resulting in a visually appealing and geometrically accurate simplified representation.

Plane segmentation and decimation of point clouds for 3D environment reconstruction

Three-dimensional (3D) models of environments are a promising technique for serious gaming and professional engineering applications. In this paper, we introduce a fast and memory-efficient system for the reconstruction of large-scale environments based on point clouds. Our main contribution is the emphasis on the data processing of large planes, for which two algorithms have been designed to improve the overall performance of the 3D reconstruction. First, a flatness-based segmentation algorithm is presented for plane detection in point clouds. Second, a quadtree-based algorithm is proposed for decimating the point cloud involved with the segmented plane and consequently improving the efficiency of triangulation. Our experimental results have shown that the proposed system and algorithms have a high efficiency in speed and memory for environment reconstruction. Depending on the amount of planes in the scene, the obtained efficiency gain varies between 20% and 50%.

On photo-realistic 3D reconstruction of large-scale and arbitrary-shaped environments

This paper presents a system architecture for reconstructing photorealistic and accurate 3D models of indoor environments. The system specifically targets large-scale and arbitrary-shaped environments and enables processing of data obtained with an arbitrary-chosen capturing path. The system extends the baseline Kinect Fusion algorithm with a buffering algorithm to remove scene-size capturing limitations. Beside this, the paper presents the complete chain of advanced algorithms for point cloud segmentation/decimation, camera pose correction and texture mapping with post-processing filters. The presented architecture features memory- and processor-efficient processing, such that it can be executed on a conventional PC with a mainstream GPU card at the consumer premises.

Low-Level Profiling and MARTE-Compatible Modeling of Software Components for Real-Time Systems

In this paper, we present a method for (a) profiling of individual components at high accuracy level, (b) modeling of the components with the accurate data obtained from profiling, and (c) model conversion to the MARTE profile. The resulting performance models of individual components are used at the component composition (design) phases for detailed evaluation of the performance of the designed system. Furthermore, the profiled models serve as a valid source for architecture optimization of the composed system. The presented method is a constituent part of our complete Design Space Exploration (DSE) methodology [1, 2], which involves modeling of individual components, component composition, performance analysis of the designed composition, and architecture optimization. The contribution of this new profiling method is attractive in various ways: (a) The profiling is fast and detailed, which leads to accurate models, (b) it is generic, since it allows multiplatform execution and (c) it can be used by MARTE-based analysis tools, due to the model compatibility. Our discussed experiment has resulted in cycle-accurate models in less than 1 hour profiling effort per component.

Fast planar segmentation of depth images

One of the major challenges for applications dealing with the 3D concept is the real-time execution of the algorithms. Besides this, for the indoor environments, perceiving the geometry of surrounding structures plays a prominent role in terms of application performance. Since indoor structures mainly consist of planar surfaces, fast and accurate detection of such features has a crucial impact on quality and functionality of the 3D applications, e.g. decreasing model size (decimation), enhancing localization, mapping, and semantic reconstruction. The available planar-segmentation algorithms are mostly developed using surface normals and/or curvatures. Therefore, they are computationally expensive and challenging for real-time performance. In this paper, we introduce a fast planar-segmentation method for depth images avoiding surface normal calculations. Firstly, the proposed method searches for 3D edges in a depth image and finds the lines between identified edges. Secondly, it merges all the points on each pair of intersecting lines into a plane. Finally, various enhancements (e.g. filtering) are applied to improve the segmentation quality. The proposed algorithm is capable of handling VGA-resolution depth images at a 6 FPS frame-rate with a single-thread implementation. Furthermore, due to the multi-threaded design of the algorithm, we achieve a factor of 10 speedup by deploying a GPU implementation.