“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Deep learning in agriculture: A survey

We propose a semi-direct monocular visual odometry algorithm that is precise, robust, and faster than current state-of-the-art methods. The semi-direct approach eliminates the need of costly feature extraction and robust matching techniques for motion estimation. Our algorithm operates directly on pixel intensities, which results in subpixel precision at high frame-rates. A probabilistic mapping method that explicitly models outlier measurements is used to estimate 3D points, which results in fewer outliers and more reliable points. Precise and high frame-rate motion estimation brings increased robustness in scenes of little, repetitive, and high-frequency texture. The algorithm is applied to micro-aerial-vehicle state-estimation in GPS-denied environments and runs at 55 frames per second on the onboard embedded computer and at more than 300 frames per second on a consumer laptop. We call our approach SVO (Semi-direct Visual Odometry) and release our implementation as open-source software.

/pdf/svo-fast-semi-direct-monocular-visual-odometry-46fauoqkah.pdf

SVO: Fast semi-direct monocular visual odometry

Visual odometry (VO) is the process of estimating the egomotion of an agent (e.g., vehicle, human, and robot) using only the input of a single or If multiple cameras attached to it. Application domains include robotics, wearable computing, augmented reality, and automotive. The term VO was coined in 2004 by Nister in his landmark paper. The term was chosen for its similarity to wheel odometry, which incrementally estimates the motion of a vehicle by integrating the number of turns of its wheels over time. Likewise, VO operates by incrementally estimating the pose of the vehicle through examination of the changes that motion induces on the images of its onboard cameras. For VO to work effectively, there should be sufficient illumination in the environment and a static scene with enough texture to allow apparent motion to be extracted. Furthermore, consecutive frames should be captured by ensuring that they have sufficient scene overlap.

Visual Odometry [Tutorial]

Visual SLAM (simultaneous localization and mapping) refers to the problem of using images, as the only source of external information, in order to establish the position of a robot, a vehicle, or a moving camera in an environment, and at the same time, construct a representation of the explored zone. SLAM is an essential task for the autonomy of a robot. Nowadays, the problem of SLAM is considered solved when range sensors such as lasers or sonar are used to built 2D maps of small static environments. However SLAM for dynamic, complex and large scale environments, using vision as the sole external sensor, is an active area of research. The computer vision techniques employed in visual SLAM, such as detection, description and matching of salient features, image recognition and retrieval, among others, are still susceptible of improvement. The objective of this article is to provide new researchers in the field of visual SLAM a brief and comprehensible review of the state-of-the-art.

Visual simultaneous localization and mapping: a survey

Motion sensors as inertial measurement units (IMU) are widely used in robotics, for instance in the navigation and mapping tasks. Nowadays, many low cost micro electro mechanical systems (MEMS) based IMU are available off the shelf, while smartphones and similar devices are almost always equipped with low-cost embedded IMU sensors. Nevertheless, low cost IMUs are affected by systematic error given by imprecise scaling factors and axes misalignments that decrease accuracy in the position and attitudes estimation. In this paper, we propose a robust and easy to implement method to calibrate an IMU without any external equipment. The procedure is based on a multi-position scheme, providing scale and misalignments factors for both the accelerometers and gyroscopes triads, while estimating the sensor biases. Our method only requires the sensor to be moved by hand and placed in a set of different, static positions (attitudes). We describe a robust and quick calibration protocol that exploits an effective parameterless static filter to reliably detect the static intervals in the sensor measurements, where we assume local stability of the gravity's magnitude and stable temperature. We first calibrate the accelerometers triad taking measurement samples in the static intervals. We then exploit these results to calibrate the gyroscopes, employing a robust numerical integration technique. The performances of the proposed calibration technique has been successfully evaluated via extensive simulations and real experiments with a commercial IMU provided with a calibration certificate as reference data.

https://www.dis.uniroma1.it/~pretto/papers/tpm_icra2014.pdf

A Robust and Easy to Implement Method for IMU Calibration without External Equipments

In this paper we present a perception system for agriculture robotics that enables an unmanned ground vehicle (UGV) equipped with a multi spectral camera to automatically perform the crop/weed detection and classification tasks in real-time. Our approach exploits a pipeline that includes two different convolutional neural networks (CNNs) applied to the input RGB+near infra-red (NIR) images. A lightweight CNN is used to perform a fast and robust, pixel-wise, binary image segmentation, in order to extract the pixels that represent projections of 3D points that belong to green vegetation. A deeper CNN is then used to classify the extracted pixels between the crop and weed classes. A further important contribution of this work is a novel unsupervised dataset summarization algorithm that automatically selects from a large dataset the most informative subsets that better describe the original one. This enables to streamline and speed-up the manual dataset labeling process, otherwise extremely time consuming, while preserving good classification performance. Experiments performed on different datasets taken from a real farm robot confirm the effectiveness of our approach.

/pdf/fast-and-accurate-crop-and-weed-identification-with-4atpe3z3yd.pdf

Fast and Accurate Crop and Weed Identification with Summarized Train Sets for Precision Agriculture

The localization problem for an autonomous robot moving in a known environment is a well-studied problem which has seen many elegant solutions. Robot localization in a dynamic environment populated by several moving obstacles, however, is still a challenge for research. In this paper, we use an omnidirectional camera mounted on a mobile robot to perform a sort of scan matching. The omnidirectional vision system finds the distances of the closest color transitions in the environment, mimicking the way laser rangefinders detect the closest obstacles. The similarity of our sensor with classical rangefinders allows the use of practically unmodified Monte Carlo algorithms, with the additional advantage of being able to easily detect occlusions caused by moving obstacles. The proposed system was initially implemented in the RoboCup Middle-Size domain, but the experiments we present in this paper prove it to be valid in a general indoor environment with natural color transitions. We present localization experiments both in the RoboCup environment and in an unmodified office environment. In addition, we assessed the robustness of the system to sensor occlusions caused by other moving robots. The localization system runs in real-time on low-cost hardware.

Omnidirectional vision scan matching for robot localization in dynamic environments

Motion blur is a severe problem in images grabbed by legged robots and, in particular, by small humanoid robots. Standard feature extraction and tracking approaches typically fail when applied to sequences of images strongly affected by motion blur. In this paper, we propose a new feature detection and tracking scheme that is robust even to non-uniform motion blur. Furthermore, we developed a framework for visual odometry based on features extracted out of and matched in monocular image sequences. To reliably extract and track the features, we estimate the point spread function (PSF) of the motion blur individually for image patches obtained via a clustering technique and only consider highly distinctive features during matching. We present experiments performed on standard datasets corrupted with motion blur and on images taken by a camera mounted on walking small humanoid robots to show the effectiveness of our approach. The experiments demonstrate that our technique is able to reliably extract and match features and that it is furthermore able to generate a correct visual odometry, even in presence of strong motion blur effects and without the aid of any inertial measurement sensor.

/pdf/a-visual-odometry-framework-robust-to-motion-blur-dmjohvcsxt.pdf

A visual odometry framework robust to motion blur

Precision agriculture is gaining increasing attention because of the possible reduction of agricultural inputs (e.g., fertilizers and pesticides) that can be obtained by using hightech equipment, including robots. In this paper, we focus on an agricultural robotics system that addresses the weeding problem by means of selective spraying or mechanical removal of the detected weeds. In particular, we describe a deep learning based method to allow a robot to perform an accurate weed/crop classification using a sequence of two Convolutional Neural Networks (CNNs) applied to RGB images. The first network, based on an encoder-decoder segmentation architecture, performs a pixelwise, plant-type agnostic, segmentation between vegetation and soil that enables to extract a set of connected blobs representing plant instances. We show that such network can be trained also using external, ready to use pixel-wise labeled data sets coming from different contexts. Each plant is hence classified between crop and weeds by using the second network. Quantitative experimental results, obtained on real world data, demonstrate that the proposed approach can achieve good classification results also on challenging images.

Alberto Pretto

Papers

A Robust and Easy to Implement Method for IMU Calibration without External Equipments

Fast and Accurate Crop and Weed Identification with Summarized Train Sets for Precision Agriculture

Omnidirectional vision scan matching for robot localization in dynamic environments

A visual odometry framework robust to motion blur

Crop and Weeds Classification for Precision Agriculture Using Context-Independent Pixel-Wise Segmentation