Supplementary material: Strengthening the Effectiveness of Pedestrian Detection with Spatially Pooled Features
نویسندگان
چکیده
Notation Vectors are denoted by lower-case bold letters, e.g., x, matrices are denoted by upper-case bold letters, e.g., X and sets are denoted by calligraphic upper-case letters, e.g., X. All vectors are assumed to be column vectors. The (i, j) entry of X is xij . Let {x+i }i=1 be a set of pedestrian training examples and {xj }j=1 be a set of non-pedestrian training examples. The tuple of all training samples is written as S = (S+,S−) where S+ = (x + 1 , · · · ,xm) ∈ X and S− = (x − 1 , · · · ,xn ) ∈ X. In this paper, we are interested in the partial AUC (area under the ROC curve) within a specific false positive range [α, β]. Given n negative training samples, we let jα = dnαe and jβ = bnβc. Let Zβ = ( S− jβ ) denote the
منابع مشابه
Strengthening the Effectiveness of Pedestrian Detection with Spatially Pooled Features
We propose a simple yet effective approach to the problem of pedestrian detection which outperforms the current state-of-the-art. Our new features are built on the basis of low-level visual features and spatial pooling. Incorporating spatial pooling improves the translational invariance and thus the robustness of the detection process. We then directly optimise the partial area under the ROC cu...
متن کاملIndividualness and Determinantal Point Processes for Pedestrian Detection: Supplementary Material
In this supplementary material, we describe experimental results which were not included in the paper due to the page limitation. Comparisons of NMS, QUBO, and the proposed method are provided in Section 1. A sensitivity analysis of parameters is reported in Section 2. Section 3 shows the effectiveness of the proposed quality and similarity term design by comparing it to other models. Fig. 1. D...
متن کاملSupplementary Material for On Compact Codes for Spatially Pooled Features
001 002 003 004 005 006 007 008 009 010 011 012 013 014 015 016 017 018 019 020 021 022 023 024 025 026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 045 046 047 048 049 050 051 052 053 054 055 056 057 058 059 060 061 062 063 064 065 066 067 068 069 070 071 072 073 074 075 076 077 078 079 080 081 082 083 084 085 086 087 088 089 090 091 092 093 094 095 096 097 098 099 1...
متن کاملTen years of pedestrian detection, what have we learned? Supplementary material
The idea behind the experiments in section 4.1 of the main paper is to demonstrate that, within a single framework, varying the features can replicate the jump in detection performance over a ten-year span (2004 2014), i.e. the jump in performance between VJ and the current state-of-the-art. See figure 1 for results on INRIA and Caltech-USA of the following methods (all based on SquaresChnFtrs,...
متن کاملPedestrian Detection in Infrared Outdoor Images Based on Atmospheric Situation Estimation
Observation in absolute darkness and daytime under every atmospheric situation is one of the advantages of thermal imaging systems. In spite of increasing trend of using these systems, there are still lots of difficulties in analysing thermal images due to the variable features of pedestrians and atmospheric situations. In this paper an efficient method is proposed for detecting pedestrians in ...
متن کامل