This paper presents control and coordination algorithms for groups of vehicles. The focus is on autonomous vehicle networks performing distributed sensing tasks where each vehicle plays the role of a mobile tunable sensor. The paper proposes gradient descent algorithms for a class of utility functions which encode optimal coverage and sensing policies. The resulting closed-loop behavior is adaptive, distributed, asynchronous, and verifiably correct.

Coverage control for mobile sensing networks

In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to:  • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information.  Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

IEEE transactions on pattern analysis and machine intelligence

Morphometric tools for landmark data: geometry and biology

In recent years there have been excellent results in visual-inertial odometry techniques, which aim to compute the incremental motion of the sensor with high accuracy and robustness. However, these approaches lack the capability to close loops and trajectory estimation accumulates drift even if the sensor is continually revisiting the same place. In this letter, we present a novel tightly coupled visual-inertial simultaneous localization and mapping system that is able to close loops and reuse its map to achieve zero-drift localization in already mapped areas. While our approach can be applied to any camera configuration, we address here the most general problem of a monocular camera, with its well-known scale ambiguity. We also propose a novel IMU initialization method, which computes the scale, the gravity direction, the velocity, and gyroscope and accelerometer biases, in a few seconds with high accuracy. We test our system in the 11 sequences of a recent micro-aerial vehicle public dataset achieving a typical scale factor error of 1% and centimeter precision. We compare to the state-of-the-art in visual-inertial odometry in sequences with revisiting, proving the better accuracy of our method due to map reuse and no drift accumulation.

/pdf/visual-inertial-monocular-slam-with-map-reuse-qzzpcqq1e3.pdf

Visual-Inertial Monocular SLAM With Map Reuse

Over the past few years, the application of camera-equipped Unmanned Aerial Vehicles (UAVs) for visually monitoring construction and operation of buildings, bridges, and other types of civil infrastructure systems has exponentially grown. These platforms can frequently survey construction sites, monitor work-in-progress, create documents for safety, and inspect existing structures, particularly for hard-to-reach areas. The purpose of this paper is to provide a concise review of the most recent methods that streamline collection, analysis, visualization, and communication of the visual data captured from these platforms, with and without using Building Information Models (BIM) as a priori information. Specifically, the most relevant works from Civil Engineering, Computer Vision, and Robotics communities are presented and compared in terms of their potential to lead to automatic construction monitoring and civil infrastructure condition assessment.

/pdf/visual-monitoring-of-civil-infrastructure-systems-via-camera-7xo7w3ojtr.pdf

Visual monitoring of civil infrastructure systems via camera-equipped Unmanned Aerial Vehicles (UAVs): a review of related works

Estimating the 6D pose of objects is beneficial for robotics tasks such as transportation, autonomous navigation, manipulation as well as in scenarios beyond robotics like virtual and augmented reality. With respect to single image pose estimation, pose tracking takes into account the temporal information across multiple frames to overcome possible detection inconsistencies and to improve the pose estimation efficiency. In this work, we introduce a novel Deep Neural Network (DNN) called VIPose, that combines inertial and camera data to address the object pose tracking problem in real-time. The key contribution is the design of a novel DNN architecture which fuses visual and inertial features to predict the objects' relative 6D pose between consecutive image frames. The overall 6D pose is then estimated by consecutively combining relative poses. Our approach shows remarkable pose estimation results for heavily occluded objects that are well known to be very challenging to handle by existing state-of-the-art solutions. The effectiveness of the proposed approach is validated on a new dataset called VIYCB with RGB image, IMU data, and accurate 6D pose annotations created by employing an automated labeling technique. The approach presents accuracy performances comparable to state-of-the-art techniques, but with the additional benefit of being real-time.

VIPose: Real-time Visual-Inertial 6D Object Pose Tracking.

Real-time semantic image segmentation on platforms subject to size, weight and power (SWaP) constraints is a key area of interest for air surveillance and inspection. In this work, we propose MAVNet: a small, light-weight, deep neural network for real-time semantic segmentation on micro Aerial Vehicles (MAVs). MAVNet, inspired by ERFNet, features 400 times fewer parameters and achieves comparable performance with some reference models in empirical experiments. Our model achieves a trade-off between speed and accuracy, achieving up to 48 FPS on an NVIDIA 1080Ti and 9 FPS on the NVIDIA Jetson Xavier when processing high resolution imagery. Additionally, we provide two novel datasets that represent challenges in semantic segmentation for real-time MAV tracking and infrastructure inspection tasks and verify MAVNet on these datasets. Our algorithm and datasets are made publicly available.

MAVNet: an Effective Semantic Segmentation Micro-Network for MAV-based Tasks

In recent years, compact and efficient scene understanding representations have gained popularity in increasing situational awareness and autonomy of robotic systems. In this work, we illustrate the concept of a panoptic edge segmentation and propose PENet, a novel detection network called that combines semantic edge detection and instance-level perception into a compact panoptic edge representation. This is obtained through a joint network by multi-task learning that concurrently predicts semantic edges, instance centers and offset flow map without bounding box predictions exploiting the cross-task correlations among the tasks. The proposed approach allows extending semantic edge detection to panoptic edge detection which encapsulates both category-aware and instance-aware segmentation. We validate the proposed panoptic edge segmentation method and demonstrate its effectiveness on the real-world Cityscapes dataset.

PENet: A Joint Panoptic Edge Detection Network

The ability to maneuver micro aerial vehicles (MAVs) precisely relative to specific targets and to interact with the environment (i.e., aerial manipulation) could benefit society by assisting with dangerous jobs, providing useful information, and improving the efficiency of many tasks. For example, precise relative positioning would allow for close inspections of bridges, cell towers, rooftops, or water towers. Aerial manipulation could improve or enable precision farming, construction, repairing structures, transportation of objects, automated recharging or battery replacement, environmental sampling, or perching to turn off motors and reduce power consumption. The prevalence of commercially available MAVs has risen rapidly, but platforms are currently limited to sensing and data collection tasks. Indeed, many manufacturers are producing aerial robots equipped with cameras. However, none are able to physically interact with objects. Thus, there is a need for solutions empowering aerial robots to closely track, grasp, perch on, and manipulate specific objects of interest. Here, we present an overview of current approaches and challenges for vision-based perching and aerial manipulation. A more extensive discussion is available elsewhere.1 Many existing perching and grasping methods assume that the states of the robot and target are known,2–9 which is a poor assumption and motivates the search for solutions using onboard sensors. Visual-inertial approaches are appealing because the sensors are lightweight, complement each other well, and are sufficient for navigation in unknown environments.10, 11 However, in these cases, the vehicle is controlled with respect to a fixed reference frame, not specific objects. A more appropriate Figure 1. A sample perch sequence. The quadrotor carries a camera, an onboard inertial measurement unit, a computer (ODROID-Xu3), and a gripper to perch on cylinders at various orientations. All sensing and computation occurs onboard the 722g robot.

Giuseppe Loianno

Papers

VIPose: Real-time Visual-Inertial 6D Object Pose Tracking.

MAVNet: an Effective Semantic Segmentation Micro-Network for MAV-based Tasks

PENet: A Joint Panoptic Edge Detection Network

Autonomous perching and grasping for micro aerial vehicles

Automated Flight Enabled by Consumer Electronics