A Boundary-Fragment-Model for Object Detection

Abstract

Abstract. The objective of this work is the detection of object classes, such as airplanes or horses. Instead of using a model based on salient image fragments, we show that object class detection is also possible using only the object's boundary. To this end, we develop a novel learning technique to extract class-discriminative boundary fragments. In addition to their shape, these "codebook" entries also determine the object's centroid (in the manner of Leibe et al. [19]). Boosting is used to select discriminative combinations of boundary fragments (weak detectors) to form a strong "Boundary-Fragment-Model" (BFM) detector. The generative aspect of the model is used to determine an approximate segmentation.We demonstrate the following results: (i) the BFM detector is able to represent and detect object classes principally defined by their shape, rather than their appearance; and (ii) in comparison with other published results on several object classes (airplanes, cars-rear, cows) the BFM detector is able to exceed previous performances, and to achieve this with less supervision (such as the number of training images).

A survey on face detection in the wild: Past, present and future

“…For instance, in [94] multiple boundary fragments to weak classifiers were composed and formed a strong "boundary-fragment-model" detector using boosting. They ensured the feasibility of the feature selection process by limiting the number of boundary fragments to 2-3 for each weak classifier.…”

“…A number of follow-up works showed that there is indeed information in the results from the previous nodes, and it is best to reuse them [80,19] etc. Spectral histogram [86] Spatial histogram (LBP-based) [87] HoG and LBP [88] Region covariance [89] SURF [102,103] Composite Joint Haar-like features [62] features Sparse feature set [90] LGB, BHOG [22] Integral Channel Features on HoG and LUV (Headhunter) [26] HoG, HSV, RGB, LUV, Grayscale, Gradient Magnitude [105] Shape features Boundary/contour fragments [94,95] Edgelet [96] Shapelet [97] instead of starting from scratch at each new node. For instance, in [110], the use of a "chain" structure was proposed to integrate historical knowledge into successive boosting learning.…”

Fast Detection of Multiple Textureless 3-D Objects

“…In contrast, we want to use only edges that are discriminative for object detection. It has been an important topic in shape matching and detection to learn discriminative edges and discard unstable ones [14,16]. We use two criteria to select edges: stability to viewpoint and frequency of edge orientations.…”

Circle Detection Based on Voting for Maximum Compatibility

“…The experimental setup is the same as coin detection, except that some parameters are tuned to fit the task. Test images are all normalized to 1654, searching range uses [10,80], and the number of searching radii chooses 15. Other parameters are set using the same way as coin detection.…”