# Fast Shadow Detection from a Single Image Using a Patched Convolutional Neural Network Source: [Fast Shadow Detection from a Single Image Using a Patched Convolutional Neural Network]() Collection index: [llms.txt]() Data updated: 2025-12-25T02:54:16.636Z Authors: Sepideh Hosseinzadeh, Moein Shakeri, Hong Zhang Published: 2017-09-26T23:20:42.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Shadow Detection on Combined Dataset (UCF, UIUC, SBU) 1.0 (test)](): Shadow Detection; Combined Dataset (UCF, UIUC, SBU) 1.0 (test); Accuracy: 91.03. - [Shadow Detection Resource Usage on SBU](): Shadow Detection; SBU; Testing Time (hours): 0.33. - [Shadow Detection on Combined Dataset](): Shadow Detection; Combined Dataset; Testing Time (hours): 0.55. - [Shadow Detection on SBU](): Shadow Detection; SBU; BER: 11.56. - [Shadow Detection on SBU (test)](): Shadow Detection; SBU (test); Balanced Error Rate (BER): 11.56. ## Original sources and implementation [Original paper]() [PDF]()