# PAFBenchmark **Repository Path**: WLLwssy/PAFBenchmark ## Basic Information - **Project Name**: PAFBenchmark - **Description**: No description available - **Primary Language**: Unknown - **License**: Apache-2.0 - **Default Branch**: master - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2024-05-22 - **Last Updated**: 2024-05-22 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README README.md

Benchmark Datasets for Pedestrian Detection, Action Recognition, and Fall Detection

Shu Miao，Guang Chen，Xiangyu Ning，Yang Zi

Institute of Intelligent Network Vehicle, Unversity of Tongji, Shanghai, China

  1. Recording Scene and Equipment

The characteristics of the three datasets are summarized in Table 1, and they are described in detail below.

  1. How to Get Datasets

Because we upload all the data to the cloud server, if the user needs any dataset, you can click the corresponding download address.

  1. How to Handle Datasets

Conventional methods cannot process event data directly. Thus, we employ three encoding approaches59here as Frequency,SAE, (Surface of Active Events)and LIF, (Leaky60Integrate-and-Fire) to process continuous DVS event stream into a sequence of frame61images, in order to fit for conventional deep learning algorithms. We provide our codes (in Python) respect to three encoding approaches shown in folders.

  1. Contacts

Questions about these datasets should be directed to: guang@in.tum.de