papers AI Learner
The Github is limit! Click to go to the new site.

Reduced Memory Region Based Deep Convolutional Neural Network Detection

2016-09-08
Denis Tome', Luca Bondi, Emanuele Plebani, Luca Baroffio, Danilo Pau, Stefano Tubaro

Abstract

Accurate pedestrian detection has a primary role in automotive safety: for example, by issuing warnings to the driver or acting actively on car’s brakes, it helps decreasing the probability of injuries and human fatalities. In order to achieve very high accuracy, recent pedestrian detectors have been based on Convolutional Neural Networks (CNN). Unfortunately, such approaches require vast amounts of computational power and memory, preventing efficient implementations on embedded systems. This work proposes a CNN-based detector, adapting a general-purpose convolutional network to the task at hand. By thoroughly analyzing and optimizing each step of the detection pipeline, we develop an architecture that outperforms methods based on traditional image features and achieves an accuracy close to the state-of-the-art while having low computational complexity. Furthermore, the model is compressed in order to fit the tight constrains of low power devices with a limited amount of embedded memory available. This paper makes two main contributions: (1) it proves that a region based deep neural network can be finely tuned to achieve adequate accuracy for pedestrian detection (2) it achieves a very low memory usage without reducing detection accuracy on the Caltech Pedestrian dataset.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1609.02500

PDF

https://arxiv.org/pdf/1609.02500


Similar Posts

Comments