Chapter 12 - Semantic scene segmentation for robotics

Panoptic Segmentation aims to provide an understanding of background (stuff) and instances of objects (things) at a pixel level. It combines the separate tasks of semantic segmentation (pixel level classification) and instance segmentation to build a single unified scene understanding task. Typically, panoptic segmentation is derived by combining semantic and instance segmentation tasks that are learned separately or jointly (multi-task networks). In general, instance segmentation networks are built by adding a foreground mask estimation layer on top of object detectors or using instance clustering methods that assign a pixel to an instance center. In this work, we present a fully convolution neural network that learns instance segmentation from semantic segmentation and instance contours (boundaries of things). Instance contours along with semantic segmentation yield a boundary aware semantic segmentation of things. Connected component labeling on these results produces instance segmentation. We merge semantic and instance segmentation results to output panoptic segmentation. We evaluate our proposed method on the CityScapes dataset to demonstrate qualitative and quantitative performances along with several ablation studies. Our overview video can be accessed from https://youtu.be/wBtcxRhG3e0.

The field of continual deep learning is an emerging field and a lot of progress has been made. However, concurrently most of the approaches are only tested on the task of image classification, which is not relevant in the field of intelligent vehicles. Only recently approaches for class-incremental semantic segmentation were proposed. However, all of those approaches are based on some form of knowledge distillation. At the moment there are no investigations on replay-based approaches that are commonly used for object recognition in a continual setting. At the same time while unsupervised domain adaption for semantic segmentation gained a lot of traction, investigations regarding domain-incremental learning in an continual setting is not well-studied. Therefore, the goal of our work is to evaluate and adapt established solutions for continual object recognition to the task of semantic segmentation and to provide baseline methods and evaluation protocols for the task of continual semantic segmentation. We firstly introduce evaluation protocols for the class- and domain-incremental segmentation and analyze selected approaches. We show that the nature of the task of semantic segmentation changes which methods are most effective in mitigating forgetting compared to image classification. Especially, in class-incremental learning knowledge distillation proves to be a vital tool, whereas in domain-incremental learning replay methods are the most effective method.

Abstract. Semantic instance segmentation from scenes, serving as a crucial role for 3D modelling and scene understanding. Conducting semantic segmentation before grouping instances is adopted by the existing state-of-the-art methods. However, without additional refinement, semantic errors will fully propagate into the grouping stage, resulting in low overlap with the ground truth instance. Furthermore, the proposed methods focused on indoor level scenes, which are limited when directly applied to large-scale outdoor Airborne Laser Scanning (ALS) point clouds. Numerous instances, significant object density and scale variations make ALS point clouds distinct from indoor data. In order to address the problems, we proposed a geometric characterization-aware semantic instance segmentation network, which utilized both semantic and objectness score to select potential points for grouping. And in point cloud feature learning stage, hand-craft geometry features are taken as input for geometric characterization awareness. Moreover, to address errors propagated from previous modules after grouping, we have additionally designed a per-instance refinement module. To assess semantic instance segmentation, we conducted experiments on an open-source dataset. Additionally, we performed semantic segmentation experiments to evaluate the performance of our proposed point cloud feature learning method.

Research on image classification sparked the latest deep-learning boom. Many downstream tasks, including semantic segmentation, benefit from it. The state-of-the-art semantic segmentation models are all based on deep learning, and they sometimes make some semantic mistakes. In a semantic segmentation dataset with a small number of categories, images are often collected from a single scene, and there is a close semantic connection between any two categories. However, in the semantic segmentation dataset collected from multiple scenes, two categories may be irrelevant. The probability of objects in one category appearing next to objects in other categories is different, which is the basis of the paper. Semantic segmentation methods need to solve two problems of positioning and classification. This paper is dedicated to correcting those clearly wrong classifications that are contrary to reality. Specifically, we first calculate the relevancy between different class pairs. Then, based on this knowledge, we infer the category of a connected component according to the relationships of this connected component with its surrounding connected components and correct the obviously wrong classifications made by a deep learning semantic segmentation model. Several well-performing deep learning models are experimented on two challenging public datasets in the field of semantic image segmentation. Our proposed method improves the performance of UPerNet, OCRNet and SETR from 40.7%, 43% and 48.64% to 42.07%, 44.09% and 49.09% mean IoU on the ADE20K validation set, and the performance of PSPNet, DeepLabV3 and OCRNet from 37.26%, 37.3% and 39.5% to 38.93%, 38.95% and 40.63% mean IoU on the COCO-Stuff dataset, which shows the effectiveness of the method.

As a cultural heritage, traditional dance must be protected and preserved. Pendet dance is a traditional dance from Bali, Indonesia. Dance recognition raises a complex problem for computer vision research because the features representing the dancer must focus on the dancer's entire body. This can be done by performing a segmentation task process. One type of segmentation task in computer vision is the semantic segmentation. Mask R-CNN and U-NET were employed in this task. Since it was first introduced in 2015, semantic segmentation using the U-Net architecture has been widely adopted, developed, and modified. One of the new architectures applied is the MultiRes UNet. This study carries out a semantic segmentation task on the Balinese Pendet dance image using the MultiRes UNet architecture by changing the value of α (alpha) to obtain the best results. This architectural is evaluated by DC score, Jaccard index, and MSE. In this dataset, the alpha value of 1.9 resulted in the best score for DC and the Jaccard index with 98.47% and 99.23% respectively. On the other hand, an alpha value of 1.8 obtained the best score of MSE with 8.20E-04.

Automated design of neural network architectures tailored for a specific task is an extremely promising, albeit inherently difficult, avenue to explore. While most results in this domain have been achieved on image classification and language modelling problems, here we concentrate on dense per-pixel tasks, in particular, semantic image segmentation using fully convolutional networks. In contrast to the aforementioned areas, the design choices of a fully convolutional network require several changes, ranging from the sort of operations that need to be used - e.g., dilated convolutions - to a solving of a more difficult optimisation problem. In this work, we are particularly interested in searching for high-performance compact segmentation architectures, able to run in real-time using limited resources. To achieve that, we intentionally over-parameterise the architecture during the training time via a set of auxiliary cells that provide an intermediate supervisory signal and can be omitted during the evaluation phase. The design of the auxiliary cell is emitted by a controller, a neural network with the fixed structure trained using reinforcement learning. More crucially, we demonstrate how to efficiently search for these architectures within limited time and computational budgets. In particular, we rely on a progressive strategy that terminates non-promising architectures from being further trained, and on Polyak averaging coupled with knowledge distillation to speed-up the convergence. Quantitatively, in 8 GPU-days our approach discovers a set of architectures performing on-par with state-of-the-art among compact models on the semantic segmentation, pose estimation and depth prediction tasks. Code will be made available here: https://github.com/drsleep/nas-segm-pytorch.

<p class="VARAbstract">The growing availability of three-dimensional (3D) data, such as point clouds, coming from Light Detection and Ranging (LiDAR), Mobile Mapping Systems (MMSs) or Unmanned Aerial Vehicles (UAVs), provides the opportunity to rapidly generate 3D models to support the restoration, conservation, and safeguarding activities of cultural heritage (CH). The so-called scan-to-BIM process can, in fact, benefit from such data, and they can themselves be a source for further analyses or activities on the archaeological and built heritage. There are several ways to exploit this type of data, such as Historic Building Information Modelling (HBIM), mesh creation, rasterisation, classification, and semantic segmentation. The latter, referring to point clouds, is a trending topic not only in the CH domain but also in other fields like autonomous navigation, medicine or retail. Precisely in these sectors, the task of semantic segmentation has been mainly exploited and developed with artificial intelligence techniques. In particular, machine learning (ML) algorithms, and their deep learning (DL) subset, are increasingly applied and have established a solid state-of-the-art in the last half-decade. However, applications of DL techniques on heritage point clouds are still scarce; therefore, we propose to tackle this framework within the built heritage field. Starting from some previous tests with the Dynamic Graph Convolutional Neural Network (DGCNN), in this contribution close attention is paid to: i) the investigation of fine-tuned models, used as a transfer learning technique, ii) the combination of external classifiers, such as Random Forest (RF), with the artificial neural network, and iii) the evaluation of the data augmentation results for the domain-specific ArCH dataset. Finally, after taking into account the main advantages and criticalities, considerations are made on the possibility to profit by this methodology also for non-programming or domain experts.</p><p>Highlights:</p><ul><li><p>Semantic segmentation of built heritage point clouds through deep neural networks can provide performances comparable to those of more consolidated state-of-the-art ML classifiers.</p></li><li><p>Transfer learning approaches, as fine-tuning, can considerably reduce computational time also for CH domain-specific datasets, as well as improve metrics for some challenging categories (i.e. windows or mouldings).</p></li><li><p>Data augmentation techniques do not significantly improve overall performances.</p></li></ul>

Advanced Driver Assistance System (ADAS) is a very important part of an up to date vehicle. For achieving highlevel objectives in such ADAS functionality like LKA (lane keeping assistance), LDW (lane departure warning system), FCW (forward collision warning) the quality of the algorithms under the hood must be extremely high. In the last few years, it is common that these algorithms are based on DNNs (deep neural networks) applied to the tasks of semantic and instance segmentation, 2D/3D object detection and visual object tracking. Recent state-of-the-art DNN models as usual solve only one single task from the listed above and running several neural networks is rather computationally expensive and even impossible due to the lack of the GPU memory. One of the approaches used to overcome such a problem is a shared backbone (also called feature extractor or encoder). The backbone consumes most of the computing resources thus the model with a shared backbone achieves better inference performance. Unfortunately, the training procedure for a shared backbone model has several difficulties. The first one is the lack of datasets with all the required and uniform annotation types. The second problem is a more sophisticated backpropagation procedure. In this paper, we consider several methods for multi-task neural network training and present the results of such training procedures on several public datasets with dissimilar annotation types. The shared backbone is applied to the following three tasks performed simultaneously on the road scene: semantic segmentation, 2D object detection and 3D object detection. While the performance of the DNNs with shared backbone increased significantly, we obtained the quality evaluation results, which are quite close to the original separate state-of-the-art DNNs and even outperforms them in some evaluation indices.

Semantic segmentation is an important task in self-driving cars. The aims of semantic segmentation are to recognize pre-defined objects and its pixel-by-pixel location. The most popular method in semantic segmentation is Deep learning which has considerably improved semantic image segmentation. This work does an overview for semantic segmentation using Deep learning. This works also implement comparisons in term of precision, mean IOU and processing time. Three popular algorithms are PSPNet, FCN and SegNet that are examined carefully. In detail, the aim of this work points out a trade-off between processing time and mean IOU, and also between processing time and precision. Moreover, this paper concentrates on road segmentation for embedded devices, so processing time is significantly important. This work also figures out which method is suitable for embedded devices on road segmentation.

Most of the current semantic segmentation approaches have achieved state-of-the-art performance relying on fully convolutional networks. However, the consecutive operations such as pooling or convolution striding lead to spatially disjointed object boundaries. We present a dense boundary regression architecture (DBRS2), which aims to use boundary cues to aid high-level semantic segmentation task. Specifically, we first propose a multilevel guided low-level boundary (MG-LB) learning method, where we exploit multilevel convolutional features as guidance for low-level boundary detection. The predicted MG-LB boundaries are used to enable consistent spatial grouping and enhance precise adherence to segment boundaries. Then, we present a significant global energy model based on boundary penalty and appearance penalty, which are respectively defined on the predicted boundaries and coarse segmentations obtained by the DeepLabv3 network. Finally, the refined segmentations are regressed by minimizing the global energy model. Extensive experiments over PASCAL VOC 2012, ADE20K, CamVid, and BSD500 datasets demonstrate that the proposed approach can obtain state-of-the-art performance on both semantic segmentation and boundary detection tasks.

The SAR image semantic segmentation using computer vision techniques has gained much popularity in the research community due to their wide applications. Despite the advancements in Deep Learning for image analysis, these models still struggle to segment SAR images due to the existence of speckle noise and a poor feature extractor. Moreover, deep learning models are challenging to train on small datasets and the performance of the model is significantly impacted by the quality of the data. This calls for the development of an effective network that can draw out critical information from the low resolution SAR images. In this regard, the present work proposes a unique Self attention module in U-Net for the semantic segmentation of low resolution SAR images.. The Self Attention Model makes use of Laplacian kernel to highlight the sharp discontinuities in the features that define the boundaries of the objects. The proposed model, employs dilated convolution layers at the initial layers, enabling the model to more effectively capture larger contextual information. With an accuracy of 0.84 and an F1-score of 0.83, the proposed model outperforms the state-of-the-art techniques in semantic segmentation of low resolution SAR images. The results clearly demonstrate the importance of the self attention module and the consideration of dilated convolution layers in the initial layers in semantic segmentation of low resolution SAR images.

Recent advancements in deep learning techniques tailored for autonomous driving in Indian road conditions are crucial for revolutionizing transportation systems. Indian roads present unique challenges, including unpredictable traffic patterns, diverse road infrastructures, and challenging weather conditions. Deep learning is pivotal in addressing these challenges, focusing on perception, decision-making, and control. Various architectures, including Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Deep Reinforcement Learning (DRL), are analyzed for their efficacy in autonomous driving. Sensor fusion techniques enhance perception capabilities, such as lidar, radar, and camera data integration. Additionally, advancements in semantic segmentation and object detection algorithms improve scene understanding and obstacle recognition. Collaborative efforts between academia, industry, and government agencies are essential for accelerating the deployment of autonomous driving technology in Indian road conditions. In conclusion, leveraging cutting-edge deep learning methodologies enables safe and efficient navigation of autonomous vehicles, ushering in a transformative future in transportation systems.

While current approaches for neural network training often aim at improving performance, less focus is put on training methods aiming at robustness towards varying noise conditions or directed attacks by adversarial examples. In this paper, we propose to improve robustness by a multi-task training, which extends supervised semantic segmentation by a self-supervised monocular depth estimation on unlabeled videos. This additional task is only performed during training to improve the semantic segmentation model's robustness at test time under several input perturbations. Moreover, we even find that our joint training approach also improves the performance of the model on the original (supervised) semantic segmentation task. Our evaluation exhibits a particular novelty in that it allows to mutually compare the effect of input noises and adversarial attacks on the robustness of the semantic segmentation. We show the effectiveness of our method on the Cityscapes dataset, where our multi-task training approach consistently outperforms the single-task semantic segmentation baseline in terms of both robustness vs. noise and in terms of adversarial attacks, without the need for depth labels in training.

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

Improving performance of deep learning models for 3D point cloud semantic segmentation via attention mechanisms