a new generation of computer vision, namely event-based or neuromorphic vision, provides a new paradigm for capturing visual data and the way such data is processed. Due to a highly novel type of visual sensors used in event-based vision, only a few datasets aimed at visual navigation tasks are publicly available.In this paper, we present and describe the first event-based vision dataset intended to cover visual navigation tasks for mobile robots navigating in different types of agricultural environment. The dataset might open new opportunities for the evaluation of existing and creation of new event-based visual navigation methods for use in agricultural scenes that contain a lot of vegetation, animals, and patterned objects.The new dataset was created using our own custom-designed Sensor Bundle, which was installed on a mobile robot platform. During data acquisition sessions, the platform was manually controlled. The Sensor Bundle consists of a dynamic vision sensor, a LIDAR, an RGB-D camera, and environmental sensors.In total, 21 data sequences in 12 different scenarios for the autumn season are publicly available. Each data sequence is accompanied by a video demonstrating its content and a detailed description, including known issues. The new dataset is mostly designed for Visual Odometry tasks; however, it also includes loop-closures for applying event-based visual SLAM methods.

The Dynamic Visual Sensor is considered to be a next-generation vision sensor. Since event-based vision is in its early stage of development, a small number of datasets has been created during the last decade. Dataset creation is motivated by the need for real data from one or many sensors. Temporal accuracy of data in such datasets is crucially important since the events have high temporal resolution measured in microseconds and, during an algorithm evaluation task, such type of visual data is usually fused with data from other types of sensors. The main aim of our research is to achieve the most accurate possible time synchronization between an event camera, LIDAR, and ambient environment sensors during a session of data acquisition. All the mentioned sensors as well as a stereo and a monocular camera were installed on a mobile robotic platform. In this work, a time synchronization architecture and algorithm are proposed for time synchronization with an implementation example on a PIC32 microcontroller. The overall time synchronization approach is scalable for other sensors where there is a need for accurate time synchronization between many nodes. The evaluation results of the proposed solution are reported and discussed in the paper.

An Inertial Measuring Unit (IMU) is used for measuring linear accelerations and angular velocities in 3D/2D space. IMU devices are usually designed as micro-electro-mechanical systems (MEMS), which are produced in small form factor and are widely used in robotics, mobile phones and drones. Depending on the quality of the device, they can be divided into low-cost and high-cost IMUs. The main difference between them is the accuracy of measurements and IMUs mechanical alignment on the printed circuit board. The high-cost IMUs are well calibrated and have a relatively small error and noise level for different kinds of parameters. In contrast, the low-cost IMUs have a larger error component, where body frame axes are non-orthogonal for both the accelerometer and gyroscope due to weak factory calibration, high noise and high sensitivity dependence from the temperature, misalignment of body frame due to packaging and assembly processes. This paper provides a new method for the IMU static and dynamic interval detection within the IMU calibration procedure, which is designed by other authors for the case of IMU calibration without any external equipment. This procedure uses a sequence of alternating static and dynamic intervals for accelerometer calibration and then gyroscope calibration. The accuracy of the IMU calibration procedure depends strongly on how precisely static and dynamic intervals have been detected. Otherwise, the calibration results are unsuitable. The new method for static and dynamic interval detection provides more robust and less noisy results, requires a significantly smaller number of operations and is easy to implement. The paper provides comparative results for both methods and refers to the source code for the new method.