In autonomous driving, accurate 3D lane detection using monocular cameras is important for downstream tasks. Recent CNN and Transformer approaches usually apply a two-stage model design. The first stage transforms the image feature from a front image into a bird’s-eye-view (BEV) representation. Subsequently, a sub-network processes the BEV feature to generate the 3D detection results. However, these approaches heavily rely on a challenging image feature transformation module from a perspective view to a BEV representation. In our work, we present CurveFormer++, a single-stage Transformer-based method that does not require the view transform module and directly infers 3D lane results from the perspective image features. Specifically, our approach models the 3D lane detection task as a curve propagation problem, where each lane is represented by a curve query with a dynamic and ordered anchor point set. By employing a Transformer decoder, the model can iteratively refine the 3D lane results. A curve cross-attention module is introduced to calculate similarities between image features and curve queries. To handle varying lane lengths, we employ context sampling and anchor point restriction techniques to compute more relevant image features. Furthermore, we apply a temporal fusion module that incorporates selected informative sparse curve queries and their corresponding anchor point sets to leverage historical information. In the experiments, we evaluate our approach on two publicly real-world datasets. The results demonstrate that our method provides outstanding performance compared with both CNN and Transformer based methods. We also conduct ablation studies to analyze the impact of each component.

Sport and game industry has grown rapidly in recent years due to the application of novel sensors and algorithms for quantitative analysis. For example, flying speed and spin estimation is essential to help players to improve their skills in table tennis. However, the spin estimation for a table tennis ball is challenging, as it is difficult to observe using cameras and model the aerodynamics of ball flight with spin. This article proposes a generalized aerodynamic model with variable aerodynamic coefficients to accurately represent the flying state of a table tennis ball. Analytical solutions for the aerodynamic coefficients and the acceleration due to the Magnus force are also developed for accurate ball spin estimation using pre- and postrebounding flight trajectories. The experimental results showed that compared to current state-of-the-art methods, the proposed method has achieved the best performance in angular velocity magnitude estimation for topspinning and backspinning balls. It also achieved an error of below 10° in angular velocity amplitude estimation. Using the proposed spin estimation method, our table tennis robot could strike balls with either topspin or backspin with a high success rate of up to 84.6 $%$ . Besides, the experimental results also demonstrated the potential of the proposed method in the area of table tennis training and sports-broadcasting.

Table-tennis robots still have a long way to defeat human players because of the rapid decrease in control accuracy when the ball flying speed and spin velocity increase. In this case, the challenge is to control the robot accurately within a limited time. To overcome this challenge, this article introduces a receding horizon optimization method to solve the accuracy problem of spin estimation. With the help of accurate spin information, a single-parameter-optimization-based stroke approach is developed for the robot to guarantee accuracy and efficiency simultaneously. In terms of accuracy, the proposed method achieves the best performance compared with other spin estimation algorithms, and it also achieves a stroke error of 25.13 cm and 23.93 cm for topspinning and backspinning balls, with the passing-net height error being 12.27 cm and 10.57 cm, respectively. Due to the high efficiency of the method proposed, our robot can hit a ball that has a speed of up to 10 m/s, which is a new record for the maximum ball speed that a table-tennis robot can handle to the best of our knowledge. Using the method proposed in this article achieves success rates of 90.0 $%$ and 85.0 $%$ for striking topspin and backspin balls, surpassing the respective success rates of 40.0 $%$ and 13.1 $%$ obtained by using the previous method.