Landing site positioning and descent trajectory reconstruction of Tianwen-1 on Mars

Tianwen-1 (TW-1) is the first Chinese interplanetary mission to have accomplished orbiting, landing, and patrolling in a single exploration of Mars. After safe landing, it is essential to reconstruct the descent trajectory and determine the landing site of the lander. For this purpose, we processed descent images of the TW-1 optical obstacle-avoidance sensor (OOAS) and digital orthophoto map (DOM) of the landing area using our proposed hybrid-matching method, in which the landing process is divided into two parts. In the first, crater matching is used to obtain the geometric transformations between the OOAS images and DOM to calculate the position of the lander. In the second, feature matching is applied to compute the position of the lander. We calculated the landing site of TW-1 to be 109.9259° E, 25.0659° N with a positional accuracy of 1.56 m and reconstructed the landing trajectory with a horizontal root mean squared error of 1.79 m. These results will facilitate the analyses of the obstacle-avoidance system and optimize the control strategy in the follow-up planetary-exploration missions.

Combining multiple shaded reliefs with hypsometric colouring and digital orthophotos using free and open-source software

In this paper we combined layers created from several terrain rendering techniques, namely a shaded relief rendered in the free and open-source 3D computer graphics software Blender, a hillshade created in the free and opensource Geographic Information System (GIS) software QGIS, a hypsometric coloured Digital Elevation Model (DEM) and a draped digital orthophoto. Following a recent trend in the cartographic community towards using Blender, we tried to improve the standard relief visualization in common GIS software by blending it with a shaded relief rendered in Blender. Using different QGIS blending modes and opacity values we achieved different graphic visualizations. To compare and evaluate the suitability of different rendering techniques we chose national park Risnjak located in Croatia because of its specific and diverse terrain landforms. After comparing different input layers and parameter sets, we selected the blending combination which is best suited for visualizing terrain characteristics of all Croatian national parks. The result is a shaded relief created for every national park which is combined from a shaded relief rendered in Blender, a hillshade created in QGIS, a hypsometric coloured DEM and a draped digital orthophoto.

Performance of UAV-Based Digital Orthophoto Generation for Emergency Response Applications

Unmanned Aerial Vehicles (UAVs) have been used for accurate orthophoto generation based on advanced Global Navigation Satellite System (GNSS) techniques. In recent years, the UAV systems have become an effective tool for fast monitoring of damages caused by disasters such as the earthquake hazards. The conventional orthophoto generation based on ground control points takes too much time during emergency situations. In the study, different methodologies for the processing of the acquired GNSS Positioning data for direct georeferencing of UAVs were investigated in terms of various orbit products. Evaluating the fitness for emergency response applications, the ground control points (GCPs) also used for validation of the generated orthophoto without using GCPs and based on Precise Point Positioning (PPP) approach. In this study, Ultra-Rapid, Rapid and Final PPP methods based on GNSS observations were used for direct geo-referencing. Thirteen GCPs were located at the study area for the validation of the orthophoto accuracy generated by direct geo-referencing.

Disturbed Boundaries Extraction in Coal-grain Overlap Areas With High Groundwater Levels Using UAV-based Visible and Multispectral Imagery

Coal-grain overlap areas (CGOA) with high groundwater levels are vulnerable to subsidence and water logging during a series of mining activities, which have adverse impacts on crop yields. Such damage requires full reports of disturbed boundaries for the agricultural reimbursement and ongoing reclamation. Since direct measurements are difficult in such a case because of vast, unreachable areas, so it is necessary to be able to identify out-of-production boundary (OB) and reduced-production boundary (RB) in the corresponding region. In this study, OB was extracted by setting thresholds through characteristics of the cultivated land elevation based on UAV-generated digital surface model (DSM) and digital orthophoto map (DOM). Meanwhile, aboveground biomass (AGB), the soil plant analysis development (SPAD) value of chlorophyll contents, and leaf area index (LAI), were used to select the appropriate vegetation indexes (VI) to perform a reduced-production map (RM) based on power regression (PR), exponential regression (ER), multiple linear regression (MR) and random forest (RF) algorithms. Finally, an improved OTSU segmentation algorithm was applied to extract mild RB and severe RB. The results show elevation threshold segmentation method and the improved OTSU segmentation method can accurately recognize and extract disturbed boundaries, which are consistent with the tonal difference after crop damage in the image. This study provides reference methods and theoretical supports for disturbed boundaries determination in CGOA with high groundwater levels for further agricultural compensation and reclamation processes.

Deep Learning-Based Instance Segmentation Method of Litchi Canopy from UAV-Acquired Images

Instance segmentation of fruit tree canopies from images acquired by unmanned aerial vehicles (UAVs) is of significance for the precise management of orchards. Although deep learning methods have been widely used in the fields of feature extraction and classification, there are still phenomena of complex data and strong dependence on software performances. This paper proposes a deep learning-based instance segmentation method of litchi trees, which has a simple structure and lower requirements for data form. Considering that deep learning models require a large amount of training data, a labor-friendly semi-auto method for image annotation is introduced. The introduction of this method allows for a significant improvement in the efficiency of data pre-processing. Facing the high requirement of a deep learning method for computing resources, a partition-based method is presented for the segmentation of high-resolution digital orthophoto maps (DOMs). Citrus data is added to the training set to alleviate the lack of diversity of the original litchi dataset. The average precision (AP) is selected to evaluate the metric of the proposed model. The results show that with the help of training with the litchi-citrus datasets, the best AP on the test set reaches 96.25%.

Visual Localization of the Tianwen-1 Lander Using Orbital, Descent and Rover Images

Tianwen-1, China’s first Mars exploration mission, was successfully landed in the southern part of Utopia Planitia on 15 May 2021 (UTC+8). Timely and accurately determining the landing location is critical for the subsequent mission operations. For timely localization, the remote landmarks, selected from the panorama generated by the earliest received Navigation and Terrain Cameras (NaTeCam) images, were matched with the Digital Orthophoto Map (DOM) generated by high resolution imaging camera (HiRIC) images to obtain the initial result based on the triangulation method. Then, the initial localization result was refined by the descent images received later and the NaTeCam DOM. Finally, the lander location was determined to be (25.066°N, 109.925°E). Verified by the new orbital image with the lander and Zhurong rover visible, the localization accuracy was within a pixel of the HiRIC DOM.

Deep Fusion of DOM and DSM Features for Benggang Discovery

Benggang is a typical erosional landform in southern and southeastern China. Since benggang poses significant risks to local ecological environments and economic infrastructure, it is vital to accurately detect benggang-eroded areas. Relying only on remote sensing imagery for benggang detection cannot produce satisfactory results. In this study, we propose integrating high-resolution Digital Orthophoto Map (DOM) and Digital Surface Model (DSM) data for efficient and automatic benggang discovery. The fusion of complementary rich information hidden in both DOM and DSM data is realized by a two-stream convolutional neural network (CNN), which integrates aggregated terrain and activation image features that are both extracted by supervised deep learning. We aggregate local low-level geomorphic features via a supervised diffusion-convolutional embedding branch for expressive representations of benggang terrain variations. Activation image features are obtained from an image-oriented convolutional neural network branch. The two sources of information (DOM and DSM) are fused via a gated neural network, which learns the most discriminative features for the detection of benggang. The evaluation of a challenging benggang dataset demonstrates that our method exceeds several baselines, even with limited training examples. The results show that the fusion of DOM and DSM data is beneficial for benggang detection via supervised convolutional and deep fusion networks.

Semi-Supervised Deep Learning for Lunar Crater Detection Using CE-2 DOM

Lunar craters are very important for estimating the geological age of the Moon, studying the evolution of the Moon, and for landing site selection. Due to a lack of labeled samples, processing times due to high-resolution imagery, the small number of suitable detection models, and the influence of solar illumination, Crater Detection Algorithms (CDAs) based on Digital Orthophoto Maps (DOMs) have not yet been well-developed. In this paper, a large number of training data are labeled manually in the Highland and Maria regions, using the Chang’E-2 (CE-2) DOM; however, the labeled data cannot cover all kinds of crater types. To solve the problem of small crater detection, a new crater detection model (Crater R-CNN) is proposed, which can effectively extract the spatial and semantic information of craters from DOM data. As incomplete labeled samples are not conducive for model training, the Two-Teachers Self-training with Noise (TTSN) method is used to train the Crater R-CNN model, thus constructing a new model—called Crater R-CNN with TTSN—which can achieve state-of-the-art performance. To evaluate the accuracy of the model, three other detection models (Mask R-CNN, no-Mask R-CNN, and Crater R-CNN) based on semi-supervised deep learning were used to detect craters in the Highland and Maria regions. The results indicate that Crater R-CNN with TTSN achieved the highest precision (of 91.4% and 88.5%, respectively) in the Highland and Maria regions, even obtaining the highest recall and F1 score. Compared with Mask R-CNN, no-Mask R-CNN, and Crater R-CNN, Crater R-CNN with TTSN had strong robustness and better generalization ability for crater detection within 1 km in different terrains, making it possible to detect small craters with high accuracy when using DOM data.

Positional Accuracy Assessment of Digital Orthophoto Based on UAV Images: An Experience on an Archaeological Area

Rapid development in UAV (unmanned aerial vehicle) photogrammetry made it preferable in many applications including cultural heritage documentation. Usability, quickness and accuracy of digital images have grabbed also the attention of archaeologists. Especially orthoimages by UAVs have become considerably significant in the field of archaeological heritage documentation since they are fast and accurate images of the object with high detailed information. However their accuracy and quality are the most important features of these images for archaeological documentation. The aim of this paper is to evaluate horizontal and vertical accuracy of an orthophoto taken by a fixed-wing UAV in an archaeological area. The evaluation is made according to ASPRS (American Society for Photogrammetry and Remote Sensing) Accuracy Standards for Digital Geospatial Data. The archaeological area, the name of which is Kubad Abad Palace in Beyşehir Province in Konya, is the only Anatolian Seljuk Palace structure that has survived to the present day. The study describes the orthophoto generation process and positional accuracy evaluation results within the frame of the importance of accuracy for archaeological documentation.