Bioinspired Computer Vision

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Computer Science & Engineering".

Deadline for manuscript submissions: closed (29 February 2020) | Viewed by 10093

Special Issue Editor


E-Mail Website
Guest Editor
Department of Informatics, Bioengineering, Robotics, and Systems Engineering (DIBRIS), University of Genoa. Via Dodecaneso 35, 16146 Genova, Italy
Interests: bioinspired computer vision; visual perception in VR and AR

Special Issue Information

Dear Colleagues,

Bioinspired computer vision approaches usually aim to replicate the results obtained by standard algorithms, by using neuromorphic paradigms. The performance obtained by bioinspired approaches is often lower than that of standard algorithms, both in terms of reliability of the results and in terms of speed. Today, there are many computer vision algorithms that are successfully applied in several fields, such as robotics, autonomous navigation, video surveillance, facial recognition, and, more recently, augmented reality. On the other hand, it is well known that biological vision systems are able to extract and analyze the information that is contained in complex, cluttered, and noisy environments, in order to solve vital tasks, such as navigating and recognizing shapes and persons, finding food, or escaping from danger. Biological visual systems are able to perform these tasks with both high sensitivity and strong reliability. Moreover, they are able to solve challenging computational problems, such as scene segmentation, local and global optical flow computation, 3D perception or extracting the meaning of complex objects or movements, in an efficient and quick manner.

The main aim of this Special Issue is to seek high-quality submissions that present and discuss the recent achievements in the development of bioinspired models for solving vision tasks, especially focusing on real-world complex situations and addressing modern benchmarking datasets.

The topics of interest include, but are not limited to the following:

  • Bioinspired computer vision for motion and stereo analysis
  • Bioinspired computer vision for scene understanding
  • Bioinspired computer vision for face, gesture, and shape recognition
  • Bioinspired computer vision for the real world: Robustness, learning, adaptability, self-assessment, and failure recovery
  • Performance evaluation of bioinspired approaches
  • Bioinspired computer vision for surveillance and security applications
  • Bioinspired computer vision for virtual and augmented reality applications
  • Hardware and high-performance implementations of bioinspired approaches
  • Bioinspired computer vision and deep learning

Dr. Manuela Chessa
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (3 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

14 pages, 3285 KiB  
Article
Intrinsically Distributed Probabilistic Algorithm for Human–Robot Distance Computation in Collision Avoidance Strategies
by Marcello Chiurazzi, Alessandro Diodato, Irene Vetrò, Joan Ortega Alcaide, Arianna Menciassi and Gastone Ciuti
Electronics 2020, 9(4), 548; https://doi.org/10.3390/electronics9040548 - 25 Mar 2020
Cited by 1 | Viewed by 2849
Abstract
Humans and robots are becoming co-workers, both in industrial and medical applications. This new paradigm raises problems related to human safety. To accomplish and solve this issue, many researchers have developed collision avoidance strategies—mainly relying on potential field approaches—in which attractive and repulsive [...] Read more.
Humans and robots are becoming co-workers, both in industrial and medical applications. This new paradigm raises problems related to human safety. To accomplish and solve this issue, many researchers have developed collision avoidance strategies—mainly relying on potential field approaches—in which attractive and repulsive virtual forces are generated between manipulators and objects within a collaborative workspace. The magnitude of such virtual forces strongly depends on the relative distance between the manipulators and the approaching agents, as well on their relative velocity. In this paper, authors developed an intrinsically distributed probabilistic algorithm to compute distances between the manipulator surfaces and humans, allowing tuning the computational time versus estimation accuracy, based on the application requirements. At each iteration, the algorithm computes the human–robot distances, considering all the Cartesian points within a specific geometrical domain, built around humans’ kinematic chain, and selecting a random subset of points outside of it. Experimental validation was performed in a dynamic and unstructured condition to assess the performance of the algorithm, simulating up to six humans into the shared workspace. Tests showed that the algorithm, with the selected hardware, is able to estimate the distance between the human and the manipulator with a RMSE of 5.93 mm (maximum error of 34.86 mm). Full article
(This article belongs to the Special Issue Bioinspired Computer Vision)
Show Figures

Graphical abstract

11 pages, 4274 KiB  
Article
A Signal-Processing Neural Model Based on Biological Retina
by Hui Wei, Luping Wang, Shanshan Wang, Yuxiang Jiang and Jingmeng Li
Electronics 2020, 9(1), 35; https://doi.org/10.3390/electronics9010035 - 27 Dec 2019
Cited by 3 | Viewed by 2314
Abstract
Image signal processing has considerable value in artificial intelligence. However, due to the diverse disturbance (e.g., color, noise), the image signal processing, especially the representation of the signal, remains a big challenge. In the human visual system, it has been justified that simple [...] Read more.
Image signal processing has considerable value in artificial intelligence. However, due to the diverse disturbance (e.g., color, noise), the image signal processing, especially the representation of the signal, remains a big challenge. In the human visual system, it has been justified that simple cells in the primary visual cortex are obviously sensitive to vision signals with partial orientation features. In other words, the image signals are extracted and described along the pathway of visual processing. Inspired by this neural mechanism of the primary visual cortex, it is possible to build an image signal-processing model as the neural architecture. In this paper, we presented a method to process the image signal involving a multitude of disturbance. For image signals, we first extracted 4 rivalry pathways via the projection of color. Secondly, we designed an algorithm in which the computing process of the stimulus with partial orientation features can be altered into a process of analytical geometry, resulting in that the signals with orientation features can be extracted and characterized. Finally, through the integration of characterizations from the 4 different rivalry pathways, the image signals can be effectively interpreted and reconstructed. Instead of data-driven methods, the presented approach requires no prior training. With the use of geometric inferences, the method tends to be interpreted and applied in the signal processor. The extraction and integration of rivalry pathways of different colors allow the method to be effective and robust to the signals with the image noise and disturbance of colors. Experimental results showed that the approach can extract and describing the image signal with diverse disturbance. Based on the characterization of the image signal, it is possible to reconstruct signal features which can effectively represent the important information from the original image signal. Full article
(This article belongs to the Special Issue Bioinspired Computer Vision)
Show Figures

Figure 1

20 pages, 3796 KiB  
Article
Unsupervised Monocular Depth Estimation Based on Residual Neural Network of Coarse–Refined Feature Extractions for Drone
by Tao Huang, Shuanfeng Zhao, Longlong Geng and Qian Xu
Electronics 2019, 8(10), 1179; https://doi.org/10.3390/electronics8101179 - 17 Oct 2019
Cited by 8 | Viewed by 4181
Abstract
To take full advantage of the information of images captured by drones and given that most existing monocular depth estimation methods based on supervised learning require vast quantities of corresponding ground truth depth data for training, the model of unsupervised monocular depth estimation [...] Read more.
To take full advantage of the information of images captured by drones and given that most existing monocular depth estimation methods based on supervised learning require vast quantities of corresponding ground truth depth data for training, the model of unsupervised monocular depth estimation based on residual neural network of coarse–refined feature extractions for drone is therefore proposed. As a virtual camera is introduced through a deep residual convolution neural network based on coarse–refined feature extractions inspired by the principle of binocular depth estimation, the unsupervised monocular depth estimation has become an image reconstruction problem. To improve the performance of our model for monocular depth estimation, the following innovations are proposed. First, the pyramid processing for input image is proposed to build the topological relationship between the resolution of input image and the depth of input image, which can improve the sensitivity of depth information from a single image and reduce the impact of input image resolution on depth estimation. Second, the residual neural network of coarse–refined feature extractions for corresponding image reconstruction is designed to improve the accuracy of feature extraction and solve the contradiction between the calculation time and the numbers of network layers. In addition, to predict high detail output depth maps, the long skip connections between corresponding layers in the neural network of coarse feature extractions and deconvolution neural network of refined feature extractions are designed. Third, the loss of corresponding image reconstruction based on the structural similarity index (SSIM), the loss of approximate disparity smoothness and the loss of depth map are united as a novel training loss to better train our model. The experimental results show that our model has superior performance on the KITTI dataset composed by corresponding left view and right view and Make3D dataset composed by image and corresponding ground truth depth map compared to the state-of-the-art monocular depth estimation methods and basically meet the requirements for depth information of images captured by drones when our model is trained on KITTI. Full article
(This article belongs to the Special Issue Bioinspired Computer Vision)
Show Figures

Figure 1

Back to TopTop