Performance Evaluation of Deep Learning Networks for Semantic Segmentation of Traffic Stereo-Pair Images

by   Vlad Taran, et al.

Semantic image segmentation is one the most demanding task, especially for analysis of traffic conditions for self-driving cars. Here the results of application of several deep learning architectures (PSPNet and ICNet) for semantic image segmentation of traffic stereo-pair images are presented. The images from Cityscapes dataset and custom urban images were analyzed as to the segmentation accuracy and image inference time. For the models pre-trained on Cityscapes dataset, the inference time was equal in the limits of standard deviation, but the segmentation accuracy was different for various cities and stereo channels even. The distributions of accuracy (mean intersection over union - mIoU) values for each city and channel are asymmetric, long-tailed, and have many extreme outliers, especially for PSPNet network in comparison to ICNet network. Some statistical properties of these distributions (skewness, kurtosis) allow us to distinguish these two networks and open the question about relations between architecture of deep learning networks and statistical distribution of the predicted results (mIoU here). The results obtained demonstrated the different sensitivity of these networks to: (1) the local street view peculiarities in different cities that should be taken into account during the targeted fine tuning the models before their practical applications, (2) the right and left data channels in stereo-pairs. For both networks, the difference in the predicted results (mIoU here) for the right and left data channels in stereo-pairs is out of the limits of statistical error in relation to mIoU values. It means that the traffic stereo pairs can be effectively used not only for depth calculations (as it is usually used), but also as an additional data channel that can provide much more information about scene objects than simple duplication of the same street view images.


page 2

page 3

page 4

page 5


Impact of Ground Truth Annotation Quality on Performance of Semantic Image Segmentation of Traffic Conditions

Preparation of high-quality datasets for the urban scene understanding i...

Layered Interpretation of Street View Images

We propose a layered street view model to encode both depth and semantic...

Survey on Semantic Stereo Matching / Semantic Depth Estimation

Stereo matching is one of the widely used techniques for inferring depth...

No More Discrimination: Cross City Adaptation of Road Scene Segmenters

Despite the recent success of deep-learning based semantic segmentation,...

Real-Time Semantic Stereo Matching

Scene understanding is paramount in robotics, self-navigation, augmented...

Detection and Retrieval of Out-of-Distribution Objects in Semantic Segmentation

When deploying deep learning technology in self-driving cars, deep neura...

Disparity Image Segmentation For ADAS

We present a simple solution for segmenting grayscale images using exist...

Please sign up or login with your details

Forgot password? Click here to reset