Using Channel-Wise Attention for Deep CNN Based Real-Time Semantic Segmentation with Class-Aware Edge Information

Advanced Driver Assistance Systems (ADAS) consists of two basic functions. One is the object detection for preventing vehicles from hitting pedestrians or other obstacles. The other is image segmentation for recognizing drivable areas and guiding the vehicle forward. For the latter, unlike those traditional image segmentation methods, image semantic segmentation based on deep learning architecture can handle the irregularly shaped road areas better, guiding a vehicle to drive in a more complex environment. With the popularity of Convolution Neural Networks (CNNs) in recent year, the traditional hand-crafted features methods have shown to be outperformed. However, deep CNN models are difficult to implement on vehicle application because the severe cost of time for complex processing. Although some proposed methods, such as Efficient neural network (Enet), achieved higher speed by removing some layers, it also led to the decrease of segmentation accuracy. In this research work, we propose a novel semantic segmentation network, Edgenet, which contains a class-aware edge loss module and a channel-wise attention mechanism, aiming to improve the accuracy with no harm to inference speed. We evaluate Edgenet on Cityscapes dataset, which is the most challenging and authoritative on-road semantic segmentation dataset. The results show that our proposed method can achieve over 70% mean IOU on Cityscapes test set and run at over 30 FPS in a single GTX Titan X (Maxwell) GPU.