MTSAN: Multi-Task Semantic Attention Network for ADAS Applications

نویسندگان

چکیده

This paper presents a lightweight Multi-task Semantic Attention Network (MTSAN) to collectively deal with object detection as well semantic segmentation aiding real-time applications of the Advanced Driver Assistance Systems (ADAS). proposes Module (SAM) that introduces contextual clues from subnet guide subnet. The SAM significantly boosts up performance and computational cost by considerably decreasing false alarm rate it is completely independent any other parameters. experimental results show effectiveness each component network demonstrate proposed MTSAN yields better balance between accuracy speed. Following post-processing methods, module tested proved for its in Lane Departure Warning System (LDWS) Forward Collision (FCWS). In addition, deployable on low-power embedded devices meet requirements yielding 10FPS @ 512 X 256 NVIDIA Jetson Xavier 15FPS Texas Instrument's TDA2x.

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

Enhanced Disparity Computation for ADAS Applications

Many of ADAS applications such as pedestrian and vehicle detection are using stereo vision. By computing thewell-known disparity the range of objects ahead of the car can be determined. According to the computed range, it is possible to identify whether this object is in a collision position or not. Based on the chain code algorithm a new disparity computation method is introduced. The proposed...

متن کامل

Task Partitioning for Multi-core Network Processors

Network processors (NPs) typically contain multiple concurrent processing cores. State-of-the-art programming techniques for NPs are invariably low-level, requiring programmers to partition code into concurrent tasks early in the design process. This results in programs that are hard to maintain and hard to port to alternative architectures. This paper presents a new approach in which a high-le...

متن کامل

Attention-Based Convolutional Neural Network for Semantic Relation Extraction

Nowadays, neural networks play an important role in the task of relation classification. In this paper, we propose a novel attention-based convolutional neural network architecture for this task. Our model makes full use of word embedding, part-of-speech tag embedding and position embedding information. Word level attention mechanism is able to better determine which parts of the sentence are m...

متن کامل

UoW: Multi-task Learning Gaussian Process for Semantic Textual Similarity

We report results obtained by the UoW method in SemEval-2014’s Task 10 – Multilingual Semantic Textual Similarity. We propose to model Semantic Textual Similarity in the context of Multi-task Learning in order to deal with inherent challenges of the task such as unbalanced performance across domains and the lack of training data for some domains (i.e. unknown domains). We show that the Multi-ta...

متن کامل

Semantic Segmentation via Multi-task, Multi-domain Learning

We present an approach that leverages multiple datasets possibly annotated using different classes to improve the semantic segmentation accuracy on each individual dataset. We propose a new selective loss function that can be integrated into deep networks to exploit training data coming from multiple datasets with possibly different tasks (e.g., different label-sets). We show how the gradient-r...

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 Access

سال: 2021

ISSN: ['2169-3536']

DOI: https://doi.org/10.1109/access.2021.3068991