The TriRhenaTech alliance universities and their partners presented their competences in the field of artificial intelligence and their cross-border cooperations with the industry at the tri-national conference 'Artificial Intelligence : from Research to Application' on March 13th, 2019 in Offenburg. The TriRhenaTech alliance is a network of universities in the Upper Rhine Trinational Metropolitan Region comprising of the German universities of applied sciences in Furtwangen, Kaiserslautern, Karlsruhe, and Offenburg, the Baden-Wuerttemberg Cooperative State University Loerrach, the French university network Alsace Tech (comprised of 14 'grandes \'ecoles' in the fields of engineering, architecture and management) and the University of Applied Sciences and Arts Northwestern Switzerland. The alliance's common goal is to reinforce the transfer of knowledge, research, and technology, as well as the cross-border mobility of students.
The ability to distinguish between the self and the background is of paramount importance for robotic tasks. The particular case of hands, as the end effectors of a robotic system that more often enter into contact with other elements of the environment, must be perceived and tracked with precision to execute the intended tasks with dexterity and without colliding with obstacles. They are fundamental for several applications, from Human-Robot Interaction tasks to object manipulation. Modern humanoid robots are characterized by high number of degrees of freedom which makes their forward kinematics models very sensitive to uncertainty. Thus, resorting to vision sensing can be the only solution to endow these robots with a good perception of the self, being able to localize their body parts with precision. In this paper, we propose the use of a Convolution Neural Network (CNN) to segment the robot hand from an image in an egocentric view. It is known that CNNs require a huge amount of data to be trained. To overcome the challenge of labeling real-world images, we propose the use of simulated datasets exploiting domain randomization techniques. We fine-tuned the Mask-RCNN network for the specific task of segmenting the hand of the humanoid robot Vizzy. We focus our attention on developing a methodology that requires low amounts of data to achieve reasonable performance while giving detailed insight on how to properly generate variability in the training dataset. Moreover, we analyze the fine-tuning process within the complex model of Mask-RCNN, understanding which weights should be transferred to the new task of segmenting robot hands. Our final model was trained solely on synthetic images and achieves an average IoU of 82% on synthetic validation data and 56.3% on real test data. These results were achieved with only 1000 training images and 3 hours of training time using a single GPU.
Stadelmann, Thilo, Amirian, Mohammadreza, Arabaci, Ismail, Arnold, Marek, Duivesteijn, Gilbert François, Elezi, Ismail, Geiger, Melanie, Lörwald, Stefan, Meier, Benjamin Bruno, Rombach, Katharina, Tuggener, Lukas
Deep learning with neural networks is applied by an increasing number of people outside of classic research environments, due to the vast success of the methodology on a wide range of machine perception tasks. While this interest is fueled by beautiful success stories, practical work in deep learning on novel tasks without existing baselines remains challenging. This paper explores the specific challenges arising in the realm of real world tasks, based on case studies from research \& development in conjunction with industry, and extracts lessons learned from them. It thus fills a gap between the publication of latest algorithmic and methodical developments, and the usually omitted nitty-gritty of how to make them work. Specifically, we give insight into deep learning projects on face matching, print media monitoring, industrial quality control, music scanning, strategy game playing, and automated machine learning, thereby providing best practices for deep learning in practice.
The 2020 European Conference on Computer Vision took place online, from 23 to 28 August, and consisted of 1360 papers, divided into 104 orals, 160 spotlights and the rest of 1096 papers as posters. As it is the case in recent years with ML and CV conferences, the huge number of papers can be overwhelming at times. Similar to my CVPR2020 post, to get a grasp of the general trends of the conference this year, I will present in this blog post a sort of a snapshot of the conference by summarizing some papers (& listing some) that grabbed my attention. Disclaimer: This post is not a representation of the papers and subjects presented in ECCV 2020; it is just a personnel overview of what I found interesting. The statistics presented in this section are taken from the official Opening & Awards presentation. Let's start by some general statistics: The trends of earlier years continued with more than 200% increase in submitted papers compared to the 2018 conference, and with a similar number of papers to CVPR 2020. As expected, this increase is joined by a corresponding increase in the number of reviewers and area chairs to accommodate this expansion. As expected, the majority of the accepted papers focus on topics related to deep learning, recognition, detection, and understanding. Similar to CVPR 2020, we see an increasing interest in growing areas such as label-efficient methods (e.g., unsupervised learning) and low-level vision. In terms of institutions; similar to ICML this year, Google takes the lead with 180 authors, followed by The Chinese University of Hong Kong with 140 authors and Peking University with 110 authors. In the next sections, we'll present some paper summaries by subject. The task of object detection consists of localizing and classifying objects visible given an input image. The popular framework for object detection consist of pre-defining a set of boxes (ie., a set of geometric priors like anchors or region proposals), which are first classified, followed by a regression step to the adjust the dimensions of the predefined box, and then a post-processing step to remove duplicate predictions.
The models are updated using a CNN, which ensures robustness to noise, scaling and minor variations of the targets' appearance. As with many other related approaches, an online implementation offloads most of the processing to an external server leaving the embedded device from the vehicle to carry out only minor and frequently-needed tasks. Since quick reactions of the system are crucial for proper and safe vehicle operation, performance and a rapid response of the underlying software is essential, which is why the online approach is popular in this field. Also in the context of ensuring robustness and stability, some authors apply fusion techniques to information extracted from CNN layers. It has been previously mentioned that important correlations can be drawn from deep and shallow layers which can be exploited together for identifying robust features in the data.