# Pushing the Limits of Deep CNNs for Pedestrian Detection

arXiv: https://arxiv.org/abs/1603.04525 · HTML: https://mlsanity.com/paper/1603.04525/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Mar 2016.

## Built on by (most cited first, 4 of 4)

- [Deep Learning Serves Traffic Safety Analysis: A Forward-looking Review](https://mlsanity.com/paper/2203.10939/) (2022)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)
- [A Flow-based Credibility Metric for Safety-critical Pedestrian Detection](https://mlsanity.com/paper/2402.07642/) (2024)
- [Real-Time Pedestrian Detection on IoT Edge Devices: A Lightweight Deep Learning Approach](https://mlsanity.com/paper/2409.15740/) (2024)

## Abstract (arXiv)

Compared to other applications in computer vision, convolutional neural networks have under-performed on pedestrian detection. A breakthrough was made very recently by using sophisticated deep CNN models, with a number of hand-crafted features, or explicit occlusion handling mechanism. In this work, we show that by re-using the convolutional feature maps (CFMs) of a deep convolutional neural network (DCNN) model as image features to train an ensemble of boosted decision models, we are able to achieve the best reported accuracy without using specially designed learning algorithms. We empirically identify and disclose important implementation details. We also show that pixel labelling may be simply combined with a detector to boost the detection performance. By adding complementary hand-crafted features such as optical flow, the DCNN based detector can be further improved. We set a new record on the Caltech pedestrian dataset, lowering the log-average miss rate from 11.7% to 8.9%, a relative improvement of 24%. We also achieve a comparable result to the state-of-the-art approaches on the KITTI dataset.