Automated motion detection and tracking of ground moving objects using aerial platforms is challenging due to the small object size in comparison with objects such as buildings, as well as the fact that flying cameras can undergo rapid translations and rotations. As such, our objectives are to develop a system for gathering useful information from aerial images by mapping visited areas through image mosaic king and to detect moving objects in the captured video. To do so, the Moving Objects Detection and Tracking (MODAT) framework has been developed to facilitate the application and combination of various relevant computer vision and image processing techniques in order to achieve our objectives.

Pedestrian fatality rate in Poland of 30 deaths per year per million population was the second highest among the EU countries in 2013. In the years 2007-2013 some 13% of pedestrian fatalities and 26% of injuries occurred at unsignalized pedestrian crossings where pedestrians should theoretically be safe. The paper presents results of research project MOBIS which was aimed to develop surrogate safety measures based on detection of dangerous situations or near-accidents. Within the project, pedestrian and vehicle traffic was recorded at four pedestrian crossings in Warsaw and Wrocław, for a period of approximately 2 months per crossing. Motion trajectories of vehicles and pedestrians were determined and certain parameters describing the pedestrian-vehicle encounters calculated. The average number of such encounters was over 1000 per day in both Warsaw and Wrocław. Dedicated video and data analysis algorithms were used to extract interactions that met certain criteria. To this end the following parameters were used: velocity profiles of pedestrians and vehicles, minimum distance between the participants, deceleration during braking, etc. These variables were used to develop surrogate safety indicators for pedestrian-vehicle encounters. A classification of encounters based on the characteristics of pedestrian-vehicle interaction is also proposed. Within the project certain solutions for increasing pedestrian safety at road crossings were installed and evaluated. These included speed cushions and flashing lights warning the drivers about pedestrian presence that were either mounted on traffic poles or embedded in the road surface. The evaluation of these solutions will be based on surrogate safety measures developed in the MOBIS project

Purpose – This paper seeks to develop universal software (a programming framework) enabling the implementation of service robot controllers. The software should distinguish the hardware-oriented part of the system from the task-oriented one. Moreover, force, vision as well as other sensors should be taken into account. Multi-effector systems have to be considered. Design/methodology/approach – The robot programming framework MRROC++ has been implemented as a hierarchical structure composed of processes, potentially consisting of threads. All of the software is written in an object-oriented manner using C++ and is supervised by a QNX real-time operating system. The framework has been verified on several systems executing diverse tasks. Here, a Rubik's cube puzzle-solving system, consisting of two arms and utilizing force control and visual servos, is presented. Findings – The presented framework is well suited to tasks requiring two-handed manipulation with force sensing, visual servoing and online construction of plans of actions. The Rubik's cube puzzle is a reasonable initial benchmark for validation of fundamental service robot capabilities. It requires force sensing and sight coupled with two-handed manipulation and logical reasoning, as do the majority of service tasks. Owing to the use of force sensing during manipulation, jamming of the faces has always been avoided; however, visual servoing could only cope with slow handing over of the cube due to the volume of computations associated with vision processing. Research limitations/implications – The proposed software structure does not limit the implementation of service robot controllers. However, some of the specific algorithms used for the solution of the benchmark task (i.e. Rubik's cube puzzle) need to be less time-consuming. Practical implications – The MRROC++ robot programming framework can be applied to the implementation of diverse robot controllers executing complex service tasks. Originality/value – A demanding benchmark task for service robots has been formulated. This task, as well as many others, has been used to validate the MRROC++ robot programming framework which significantly facilitates the implementation of diverse robot systems.

This paper describes the results of experiments on detection and recognition of 3D objects in RGB-D images provided by the Microsoft Kinect sensor. While the studies focus on single image use, sequences of frames are also considered and evaluated. Observed objects are categorized based on both geometrical and visual cues, but the emphasis is laid on the performance of the point cloud matching method. To this end, a rarely used approach consisting of independent VFH and CRH descriptors matching, followed by ICP and HV algorithms from the Point Cloud Library is applied. Successfully recognized objects are then subjected to a classical 2D analysis based on color histogram comparison exclusively with objects in the same geometrical category. The proposed two-stage approach allows to distinguish objects of similar geometry and different visual appearance, like soda cans of various brands. By separating geometry and color identification phases, the applied system is still able to categorize objects based on their geometry, even if there is no color match. The recognized objects are then localized in the three-dimensional space and autonomously grasped by a manipulator. To evaluate this approach, a special validation set was created, and additionally a selected scene from the Washington RGB-D Object Dataset was used.

The paper describes two crucial modules of a laser-based vision system for an underwater welding vehicle which is a joint research project of Nanyang Technological University (Singapore) and a major international corporation. The vehicle would automatically approach an underwater object, find weld seams, detect cracks and finally weld them. The first module is the ranging system. The experiments have shown that much better accuracy has been achieved when approximating polynomial functions are used instead of standard triangulation techniques. The second module detects and localises weld seams by extracting shape primitives corresponding to the expected configuration of seams from the laser-produced contours. Although the experiments are currently conducted in air, the proposed solution should be equally suitable for an underwater environment as well.