While object detection methods traditionally make use of pixel-level masks or bounding boxes, alternative representations such as polygons or active contours have recently emerged. Among them, methods based on the regression of Fourier or Chebyshev coefficients have shown high potential on freeform objects. By defining object shapes as polar functions, they are however limited to star-shaped domains. We address this issue with SCR: a method that captures resolution-free object contours as complex periodic functions. The method offers a good compromise between accuracy and compactness thanks to the design of efficient geometric shape priors. We benchmark SCR on the popular COCO 2017 instance segmentation dataset, and show its competitiveness against existing algorithms in the field. In addition, we design a compact version of our network, which we benchmark on embedded hardware with a wide range of power targets, achieving up to real-time performance.
翻译:虽然物体探测方法传统上使用像素级面罩或捆绑框,但最近出现了多边形或主动轮廓等替代表示方式,其中基于Fourier或Chebyshev系数回归的方法在自由形物体上显示出很高的潜力。通过将物体形状定义为极函数,它们却局限于恒星形状域。我们用SCR来解决这个问题:这种方法将无分辨率的物体等同作为复杂的周期函数。由于设计了高效的几何形状前缀,这种方法在准确性和紧凑性之间提供了良好的折中。我们用流行的COCO 2017例分解数据集作为SCR的基准,并显示其相对于实地现有算法的竞争力。此外,我们设计了一个我们的网络的紧凑版本,我们用嵌入的硬件作为基准,并有广泛的能量目标,达到实时性能。