The development of Advanced Driver Assistance Systems (ADAS), such as pedestrian detection, requires real-time update rates at high image resolution. Hopefully, heterogeneous architectures with high computing performance have been developed for this purpose. To benefit from this hardware performance, different programming languages and acceleration frameworks have been developed. OpenVX framework provides a graph-based execution model to program image processing algorithms on heterogeneous platforms. In this work, we investigate OpenVX optimizations for computer vision applications. We examine how this framework responds to different data access patterns. We test three important optimizations of OpenVX: kernels merge, data tiling and parallelization via OpenMP. The contribution and the impact of each optimization on different data access pattern are explained.
The indoor Visual Simultaneous Localization And Mapping (V-SLAM) dataset with various acquisition modalities has been created to evaluate the impact of acquisition modalities on the Visual SLAM algorithm’s accuracy. The dataset contains different sequences acquired with different modalities, including RGB, IR, and depth images in passive stereo and active stereo modes. Each sequence is associated with a reference trajectory constructed with an Structure From Motion (SFM) and Multi View Stereo (MVS) library for comparison. Data were collected using an intrinsically calibrated Intel RealSense D435i camera. The RGB/IR and depth data are spatially aligned, and the stereo images are rectified. The dataset includes various areas, some with low brightness, with changes in brightness, wide, narrow and texture.
Rational drug design is an approach based on detailed knowledge of molecular interactions and dynamic of bio-molecules. This approach involves designing new digital and interactive tools including classical desktop interaction devices as well as advanced ones such as haptic arms or virtual reality devices. These approaches however struggle to deal with flexibility of bio-molecules by simultaneously steering the numerous degrees of freedom. We propose a new method that follows a direct interaction approach by implementing an innovative methodology benefiting from a physical, modular and articulated molecular interface augmented by wireless embedded sensors. The goal is to create, design and steer its in silico twin virtual model and better interact with dynamic molecular models.
The dynamics of a two-wheeled vehicle represent a higher level of complexity, with a high variety of rider practices, peculiarly during the bend-taking maneuver. This complexity is one reason why research on motorcyclists’ practiced trajectories is limited compared to cars. Another reason is the low representation of motorcycles in the land motor vehicle fleet.