Pedestrian Attribute Recognition using Gabor Wavelet Layers

We address the problem of Pedestrian Attribute Recognition (PAR) in this paper. Owing to the presence of surveillance cameras in almost all outdoor and indoor public spaces, keeping and eye on pedestrian is a sought-after task with many useful applications. The problem entails recognizing attributes such as age-group, clothing style, accessories, footwear style etc. This is a multi-label problem and challenging even for human observers. We propose using a convolution neural network (CNN) with trainable Gabor wavelets (TGW) layers. The proposed layers are learnable and adapt to the dataset for a better recognition. The proposed multi-branch neural network is a mix of TGW and convolutional layers and we show its effectiveness on a public dataset.

Pedestrian attribute recognition using two-branch trainable Gabor wavelets network

Keeping an eye on pedestrians as they navigate through a scene, surveillance cameras are everywhere. With this context, our paper addresses the problem of pedestrian attribute recognition (PAR). This problem entails recognizing attributes such as age-group, clothing style, accessories, footwear style etc. This multi-label problem is extremely challenging even for human observers and has rightly garnered attention from the computer vision community. Towards a solution to this problem, in this paper, we adopt trainable Gabor wavelets (TGW) layers and cascade them with a convolution neural network (CNN). Whereas other researchers are using fixed Gabor filters with the CNN, the proposed layers are learnable and adapt to the dataset for a better recognition. We propose a two-branch neural network where mixed layers, a combination of the TGW and convolutional layers, make up the building block of our deep neural network. We test our method on twoo challenging publicly available datasets and compare our results with state of the art.