# Anchor-free Small-scale Multispectral Pedestrian Detection

arXiv: https://arxiv.org/abs/2008.08418 · HTML: https://mlsanity.com/paper/2008.08418/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2020.

## Built on by (most cited first, 8 of 8)

- [C2Former: Calibrated and Complementary Transformer for RGB-Infrared Object Detection](https://mlsanity.com/paper/2306.16175/) (2023)
- [Weakly Aligned Feature Fusion for Multimodal Object Detection](https://mlsanity.com/paper/2204.09848/) (2022)
- [Pedestrian Detection in Low-Light Conditions: A Comprehensive Survey](https://mlsanity.com/paper/2401.07801/) (2024)
- [Representation Space Constrained Learning with Modality Decoupling for Multimodal Object Detection](https://mlsanity.com/paper/2511.15433/) (2025)
- [Unifying Heterogeneous Multi-Modal Remote Sensing Detection Via Language-Pivoted Pretraining](https://mlsanity.com/paper/2603.01758/) (2026)
- [Fusion Detection via Distance-Decay IoU and weighted Dempster-Shafer Evidence Theory](https://mlsanity.com/paper/2112.03044/) (2021)
- [Person Detection Using an Ultra Low-resolution Thermal Imager on a Low-cost MCU](https://mlsanity.com/paper/2212.08415/) (2022)
- [PACGNet: Pyramidal Adaptive Cross-Gating Network for Multimodal Object Detection in Aerial Imagery](https://mlsanity.com/paper/2512.18291/) (2025)

## Abstract (arXiv)

Multispectral images consisting of aligned visual-optical (VIS) and thermal infrared (IR) image pairs are well-suited for practical applications like autonomous driving or visual surveillance. Such data can be used to increase the performance of pedestrian detection especially for weakly illuminated, small-scaled, or partially occluded instances. The current state-of-the-art is based on variants of Faster R-CNN and thus passes through two stages: a proposal generator network with handcrafted anchor boxes for object localization and a classification network for verifying the object category. In this paper we propose a method for effective and efficient multispectral fusion of the two modalities in an adapted single-stage anchor-free base architecture. We aim at learning pedestrian representations based on object center and scale rather than direct bounding box predictions. In this way, we can both simplify the network architecture and achieve higher detection performance, especially for pedestrians under occlusion or at low object resolution. In addition, we provide a study on well-suited multispectral data augmentation techniques that improve the commonly used augmentations. The results show our method's effectiveness in detecting small-scaled pedestrians. We achieve 5.68% log-average miss rate in comparison to the best current state-of-the-art of 7.49% (25% improvement) on the challenging KAIST Multispectral Pedestrian Detection Benchmark. Code: https://github.com/HensoldtOptronicsCV/MultispectralPedestrianDetection