Two papers were published at 16th International Symposium on Visual Computing:
- Evaluating User Interfaces for a Driver Guidance System to Support Stationary Wireless Charging of Electric Vehicles https://doi.org/10.1007/978-3-030-90439-5_15
- Abstract: Stationary wireless charging could be a convenient alternative to wired charging of electric vehicles. The prerequisite for efficient wireless charging is that the charging components located under the car are precisely aligned. Drivers cannot observe the state of alignment from their perspective, which makes it challenging to identify whether the vehicle’s position is accurate enough. In this paper, we present user interfaces that can support the driver in achieving the technically required precision. We provide three visualizations with different abstraction levels displayed on two screen types, which we evaluate experimentally in a user study. As part of the user study, we create a positioning scenario as it might occur with wireless charging. Participants must try to achieve the required precision by being guided by the user interfaces. The results of the user study indicate that, regardless of the visualization and screen type, drivers can position the vehicle within the defined tolerance range of 10 cm. However, the user experience differs significantly. In terms of usability and workload, drivers prefer a visualization that presents the positioning scenario from a bird’s eye view. Moreover, the time to complete the task using the bird’s eye view visualization took less than 44 s on average, which is probably shorter than parking and plugging in a charging cable. In contrast, an arrow-based visualization took in average up to 1.5 times longer than bird’s eye view visualization to complete the task and was the most criticized by the participants.
- Car Pose Estimation Through Wheel Detection https://doi.org/10.1007/978-3-030-90439-5_21
- Abstract: Car pose estimation is an essential part of different applications, including traffic surveillance, Augmented Reality (AR) guides or inductive charging assistance systems. For many systems, the accuracy of the determined pose is important. When displaying AR guides, a small estimation error can result in a different visualization, which will be directly visible to the user. Inductive charging assistance systems have to guide the driver as precise as possible, as small deviations in the alignment of the charging coils can decrease charging efficiency significantly. For accurate pose estimation, matches between image coordinates and 3d real-world points have to be determined. Since wheels are a common feature of cars, we use the wheelbase and rim radius to compute those real-world points. The matching image coordinates are obtained by three different approaches, namely the circular Hough-Transform, ellipse-detection and a neural network. To evaluate the presented algorithms, we perform different experiments: First, we compare their accuracy and time performance regarding wheel-detection in a subset of the images of The Comprehensive Cars (CompCars) dataset [37]. Second, we capture images of a car at known positions, and run the algorithms on these images to estimate the pose of the car. Our experiments show that the neural network based approach is the best in terms of accuracy and speed. However, if training of a neural network is not feasible, both other approaches are accurate alternatives.