# Fast Shadow Detection from a Single Image Using a Patched Convolutional Neural Network

arXiv: https://arxiv.org/abs/1709.09283 · HTML: https://mlsanity.com/paper/1709.09283/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Sep 2017.

## Built on by (most cited first, 7 of 7)

- [Triple-cooperative Video Shadow Detection](https://mlsanity.com/paper/2103.06533/) (2021)
- [Fine-Context Shadow Detection using Shadow Removal](https://mlsanity.com/paper/2109.09609/) (2021)
- [Unveiling Deep Shadows: A Survey and Benchmark on Image and Video Shadow Detection, Removal, and Generation in the Deep Learning Era](https://mlsanity.com/paper/2409.02108/) (2024)
- [When SAM Meets Shadow Detection](https://mlsanity.com/paper/2305.11513/) (2023)
- [AdapterShadow: Adapting Segment Anything Model for Shadow Detection](https://mlsanity.com/paper/2311.08891/) (2023)
- [SwinShadow: Shifted Window for Ambiguous Adjacent Shadow Detection](https://mlsanity.com/paper/2408.03521/) (2024)
- [Revisiting Shadow Detection from a Vision-Language Perspective](https://mlsanity.com/paper/2605.11771/) (2026)

## Abstract (arXiv)

In recent years, various shadow detection methods from a single image have been proposed and used in vision systems; however, most of them are not appropriate for the robotic applications due to the expensive time complexity. This paper introduces a fast shadow detection method using a deep learning framework, with a time cost that is appropriate for robotic applications. In our solution, we first obtain a shadow prior map with the help of multi-class support vector machine using statistical features. Then, we use a semantic- aware patch-level Convolutional Neural Network that efficiently trains on shadow examples by combining the original image and the shadow prior map. Experiments on benchmark datasets demonstrate the proposed method significantly decreases the time complexity of shadow detection, by one or two orders of magnitude compared with state-of-the-art methods, without losing accuracy.