Individualness and Determinantal Point Processes for Pedestrian Detection
In this paper, we introduce individualness of detection candidates as a complement to objectness for pedestrian detection. The individualness assigns a single detection for each object out of raw detection candidates given by either object proposals or sl
- PDF / 9,374,468 Bytes
- 17 Pages / 439.37 x 666.142 pts Page_size
- 104 Downloads / 204 Views
Electrical and Computer Engineering and ASRI, Seoul National University, Seoul, Korea {donghoon.lee,geonho.cha}@cpslab.snu.ac.kr, [email protected] 2 Electrical Engineering and Computer Science, University of California, Merced, USA [email protected]
Abstract. In this paper, we introduce individualness of detection candidates as a complement to objectness for pedestrian detection. The individualness assigns a single detection for each object out of raw detection candidates given by either object proposals or sliding windows. We show that conventional approaches, such as non-maximum suppression, are sub-optimal since they suppress nearby detections using only detection scores. We use a determinantal point process combined with the individualness to optimally select final detections. It models each detection using its quality and similarity to other detections based on the individualness. Then, detections with high detection scores and low correlations are selected by measuring their probability using a determinant of a matrix, which is composed of quality terms on the diagonal entries and similarities on the off-diagonal entries. For concreteness, we focus on the pedestrian detection problem as it is one of the most challenging problems due to frequent occlusions and unpredictable human motions. Experimental results demonstrate that the proposed algorithm works favorably against existing methods, including non-maximal suppression and a quadratic unconstrained binary optimization based method. Keywords: Determinantal point process detection · Pedestrian detection
1
·
Individualness
·
Object
Introduction
The goal of object detection is to locate objects from one known category in an image. It is essential for a number of vision tasks, such as visual tracking, scene understanding, and action recognition, to name a few. In visual tracking, tracking-by-detection is an effective approach which locates target objects in an image sequence by associating detections [1]. By learning about object locations Electronic supplementary material The online version of this chapter (doi:10. 1007/978-3-319-46466-4 20) contains supplementary material, which is available to authorized users. c Springer International Publishing AG 2016 B. Leibe et al. (Eds.): ECCV 2016, Part VI, LNCS 9910, pp. 330–346, 2016. DOI: 10.1007/978-3-319-46466-4 20
Individualness and Determinantal Point Processes for Pedestrian Detection
(a) Raw detections
(b) NMS
331
(c) Proposed method
Fig. 1. Pedestrian detection results from the INRIA dataset. (a) Raw detections in black boxes using a sliding window method. (b) Detection results from a typical nonmaximum suppression method. (c) Detection results from the proposed algorithm. Raw detection boxes A and B represent different pedestrians.
in the image, we can better understand what is happening in the scene [2]. Object detection is also applied to action recognition by finding specific items related to an action of interest [3]. The general framework for object detection is to test image patches gi
Data Loading...
