Company News

Multi-sparse Descriptor: A Scale Invariant Feature for Pedestrian Detection

|

Yazhou Liu, Pongsak Lasang, Mel W. Siegel, Quan-Sen Sun
Neurocomputing, Vol. 184, pp. 55-65, 2015.12

This paper presents a new descriptor, multi-sparse descriptor (MSD), for pedestrian detection in static images. Specifically, the proposed descriptor is based on multi-dictionary sparse coding which contains unsupervised dictionary learning and sparse coding. During unsupervised learning phase, a family of dictionaries with different representation abilities is learnt from the pedestrian data. Then the data are encoded by these dictionaries and the histogram of the sparse coefficients is calculated as the descriptor. The benefit of this multi-dictionary sparse encoding is three-fold: firstly, the dictionaries are learnt from the pedestrian data, they are more efficient for encoding local structures of the pedestrian; secondly, multiple dictionaries can enrich the representation by providing different levels of abstractions; thirdly, since the dictionaries based representation is mainly focused on the low frequency, better generalization ability along the scale range is obtained. Comparisons with the state-of-the-art methods reveal the superiority of the proposed method.

Link: https://www.sciencedirect.com/science/article/pii/S092523121501958X

Share

Related Posts

Paper accepted at NIPS2017 and another paper at CoR2017

Panasonic R&D Center Singapore, collaborating with Assistant Professor Feng Jiashi of the National University of Singapore (NUS), co-authored a paper1 titled “Dual-Agent GANs for Photorealistic and Identity Preserving Profile Face Synthesis” that has been accepted at the Conference and Workshop on Neural Information Processing Systems (NIPS) 2017

Read more

Panasonic R&D Center Singapore’s Technology – LVNet for Photo Management – Incorporated into Panasonic’s New DIGA Models to Be Commercially Launched in Japan

New models of Panasonic’s Blu-ray recorder DIGA will be launched in Japan on 16th October 2020.  (Model Name: DMR-4T401・4CT401 /…

Read more

Panasonic R&D Center Singapore Won a Silver Medal in a Kaggle Competition

Panasonic R&D Center Singapore won a silver medal in a Kaggle competition titled “Petfinder.my – Pawpularity Contest”, which started on…

Read more

Panasonic R&D Center Singapore (PRDCSG) Collaborates with Roots Innovation to Advance Human-Centric and Automotive AI Solutions

At the Smart City Summit & Expo in Taiwan. Assistant Director Pek Yew Tan (left) from Panasonic R&D Center Singapore…

Read more