A Unified Multi-Task Learning Architecture for Fast and Accurate Pedestrian Detection

نویسندگان

چکیده

We present a unified multi-task learning architecture for fast and accurate pedestrian detection. Different from existing methods which often focus on either new loss function or architecture, we propose an improved convolutional neural network to effectively efficiently interfuse the task of detection semantic segmentation. To achieve this, integrate lightweight segmentation branch Faster R-CNN framework that enables end-to-end hard parameter sharing in order boost performance maintain computational efficiency as follows. Firstly, Semantic Segmentation Feature Module (SS2FM) refines features RPN stage by integrating generated branch. Secondly, Confidence (SS2CM) classification confidence fusing it with confidence. also introduce effective anchor matching point transform alleviate problem feature misalignment heavily occluded pedestrians. The proposed lends itself well more robust diverse scenarios negligible computation overhead. In addition, can high low resolution input images, significantly reduces complexity. Experiment results CityPersons Caltech datasets show our method is fastest among all state-of-the-art while exhibiting competitive performance.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Unified Perspective on Multi-Domain and Multi-Task Learning

In this paper, we provide a new neural-network based perspective on multi-task learning (MTL) and multi-domain learning (MDL). By introducing the concept of a semantic descriptor, this framework unifies MDL and MTL as well as encompassing various classic and recent MTL/MDL algorithms by interpreting them as different ways of constructing semantic descriptors. Our interpretation provides an alte...

متن کامل

Fast Stixel Computation for Fast Pedestrian Detection

Applications using pedestrian detection in street scene require both high speed and quality. Maximal speed is reached when exploiting the geometric information provided by stereo cameras. Yet, extracting useful information at speeds higher than 100Hz is a non-trivial task. We propose a method to estimate the ground-obstacles boundary (and its distance), without computing a depth map. By properl...

متن کامل

A Unified Deep Learning Architecture for Abuse Detection

Hate speech, offensive language, sexism, racism and other types of abusive behavior have become a common phenomenon in many online social media platforms. In recent years, such diverse abusive behaviors have been manifesting with increased frequency and levels of intensity. This is due to the openness and willingness of popular media platforms, such as Twitter and Facebook, to host content of s...

متن کامل

Is Pedestrian Detection Really a Hard Task?∗

In this paper we present a simple approach for person detection in surveillance for static cameras. The basic idea is to train a separate classifier for each image location which has only to discriminate the object from the background at a specific location. This is a considerably simpler problem than the detection of persons on arbitrary backgrounds. Therefore, we use adaptive classifiers whic...

متن کامل

A Fast and Accurate Expansion-Iterative Method for Solving Second Kind Volterra Integral Equations

This article proposes a fast and accurate expansion-iterative method for solving second kind linear Volterra integral equations. The method is based on a special representation of vector forms of triangular functions (TFs) and their operational matrix of integration. By using this approach, solving the integral equation reduces to solve a recurrence relation. The approximate solution of integra...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: IEEE Transactions on Intelligent Transportation Systems

سال: 2022

ISSN: ['1558-0016', '1524-9050']

DOI: https://doi.org/10.1109/tits.2020.3019390