Importance-Aware Semantic Segmentation for Autonomous Driving System

نویسندگان

  • Bi-ke Chen
  • Chen Gong
  • Jian Yang
چکیده

Semantic Segmentation (SS) partitions an image into several coherent semantically meaningful parts, and classifies each part into one of the predetermined classes. In this paper, we argue that existing SS methods cannot be reliably applied to autonomous driving system as they ignore the different importance levels of distinct classes for safedriving. For example, pedestrians in the scene are much more important than sky when driving a car, so their segmentations should be as accurate as possible. To incorporate the importance information possessed by various object classes, this paper designs an “Importance-Aware Loss” (IAL) that specifically emphasizes the critical objects for autonomous driving. IAL operates under a hierarchical structure, and the classes with different importance are located in different levels so that they are assigned distinct weights. Furthermore, we derive the forward and backward propagation rules for IAL and apply them to deep neural networks for realizing SS in intelligent driving system. The experiments on CamVid and Cityscapes datasets reveal that by employing the proposed loss function, the existing deep learning models including FCN, SegNet and ENet are able to consistently obtain the improved segmentation results on the pre-defined important classes for safe-driving.

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

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Context-aware Architecture for Mental Model Sharing through Semantic Movement in Intelligent Agents

Recent studies in multi-agent systems are paying increasingly more attention to the paradigm of designing intelligent agents with human inspired concepts. One of the main cognitive concepts driving the core of many recent approaches in multi agent systems is shared mental models. In this paper, we propose an architecture for sharing mental models based on a new concept called semantic movement....

متن کامل

Real-Time Semantic Mapping for Autonomous Off-Road Navigation

In this paper we describe a semantic mapping system for autonomous offroad driving with an All-Terrain Vehicle (ATVs). The system’s goal is to provide a richer representation of the environment than a purely geometric map, allowing it to distinguish, e.g. tall grass from obstacles. The system builds a 2.5D grid map encoding both geometric (terrain height) and semantic information (navigation-re...

متن کامل

Fast Scene Understanding for Autonomous Driving

Most approaches for instance-aware semantic labeling traditionally focus on accuracy. Other aspects like runtime and memory footprint are arguably as important for realtime applications such as autonomous driving. Motivated by this observation and inspired by recent works that tackle multiple tasks with a single integrated architecture [13], [20], [22], in this paper we present a real-time effi...

متن کامل

Superpixel clustering with deep features for unsupervised road segmentation

Vision-based autonomous driving requires classifying each pixel as corresponding to road or not, which can be addressed using semantic segmentation. Semantic segmentation works well when used with a fully supervised model, but in practice, the required work of creating pixel-wise annotations is very expensive. Although weakly supervised segmentation addresses this issue, most methods are not de...

متن کامل

Fusion of Multispectral Data Through Illumination-aware Deep Neural Networks for Pedestrian Detection

Multispectral pedestrian detection has received extensive attention in recent years as a promising solution to facilitate robust human target detection for around-the-clock applications (e.g. security surveillance and autonomous driving). In this paper, we demonstrate illumination information encoded in multispectral images can be utilized to significantly boost performance of pedestrian detect...

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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2017