National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China.
IEEE Trans Image Process. 2013 Oct;22(10):4096-107. doi: 10.1109/TIP.2013.2270111. Epub 2013 Jun 19.
A real-time and accurate object detection framework, C(4), is proposed in this paper. C(4) achieves 20 fps speed and the state-of-the-art detection accuracy, using only one processing thread without resorting to special hardware such as GPU. The real-time accurate object detection is made possible by two contributions. First, we conjecture (with supporting experiments) that contour is what we should capture and signs of comparisons among neighboring pixels are the key information to capture contour cues. Second, we show that the CENTRIST visual descriptor is suitable for contour based object detection, because it encodes the sign information and can implicitly represent the global contour. When CENTRIST and linear classifier are used, we propose a computational method that does not need to explicitly generate feature vectors. It involves no image preprocessing or feature vector normalization, and only requires O(1) steps to test an image patch. C(4) is also friendly to further hardware acceleration. It has been applied to detect objects such as pedestrians, faces, and cars on benchmark data sets. It has comparable detection accuracy with state-of-the-art methods, and has a clear advantage in detection speed.
本文提出了一个实时、准确的目标检测框架 C(4)。C(4) 在不使用 GPU 等特殊硬件的情况下，仅使用一个处理线程，就能达到 20 fps 的速度和最先进的检测精度。通过两个贡献实现了实时准确的目标检测。首先，我们推测（通过支持性实验）轮廓是我们应该捕捉的，相邻像素之间的比较标志是捕捉轮廓线索的关键信息。其次，我们表明，CENTRIST 视觉描述符适合基于轮廓的目标检测，因为它编码了符号信息，并可以隐式地表示全局轮廓。当使用 CENTRIST 和线性分类器时，我们提出了一种不需要显式生成特征向量的计算方法。它不需要进行图像预处理或特征向量归一化，并且仅需要 O(1)步来测试图像补丁。C(4) 也便于进一步进行硬件加速。它已经被应用于在基准数据集上检测行人、面部和汽车等物体。它具有与最先进方法相当的检测精度，并且在检测速度方面具有明显优势。
