Aerial imagery can be used for important work on a global scale. Nevertheless, the analysis of this data using neural network architectures lags behind the current state-of-the-art on popular datasets such as PASCAL VOC, CityScapes and Camvid. In this paper we bridge the performance-gap between these popular datasets and aerial imagery data. Little work is done on aerial imagery with state-of-the-art neural network architectures in a multi-class setting. Our experiments concerning data augmentation, normalisation, image size and loss functions give insight into a high performance setup for aerial imagery segmentation datasets. Our work, using the state-of-the-art DeepLabv3+ Xception65 architecture, achieves a mean IOU of 70% on the DroneDeploy validation set. With this result, we clearly outperform the current publicly available state-of-the-art validation set mIOU (65%) performance with 5%. Furthermore, to our knowledge, there is no mIOU benchmark for the test set. Hence, we also propose a new benchmark on the DroneDeploy test set using the best performing DeepLabv3+ Xception65 architecture, with a mIOU score of 52.5%.
German Aerospace Center (DLR)（德国航空航天中心）；Technical University of Munich（慕尼黑工业大学）
Multi-pedestrian tracking in aerial imagery has several applications such as large-scale event monitoring, disaster management, search-and-rescue missions, and as input into predictive crowd dynamic models. Due to the challenges such as the large number and the tiny size of the pedestrians (e.g., 4 x 4 pixels) with their similar appearances as well as different scales and atmospheric conditions of the images with their extremely low frame rates (e.g., 2 fps), current state-of-the-art algorithms including the deep learning-based ones are unable to perform well. In this paper, we propose AerialM…
Deep learning is revolutionizing the mapping industry. Under lightweight human curation, computer has generated almost half of the roads in Thailand on OpenStreetMap (OSM) using high-resolution aerial imagery. Bing maps are displaying 125 million computer-generated building polygons in the U.S. While tremendously more efficient than manual mapping, one cannot map out everything from the air. Especially for roads, a small prediction gap by image occlusion renders the entire road useless for routing. Misconnections can be more dangerous. Therefore computer-based mapping often requires local veri…
The University of Melbourne（墨尔本大学）；Royal Netherlands Meteorological Institute (KNMI)（荷兰皇家气象研究所）；University of Melbourne（墨尔本大学）；Environment Protection Authority Victoria（维多利亚州环境保护局）
Analysis of overhead imagery using computer vision is a problem that has received considerable attention in academic literature. Most techniques that operate in this space are both highly specialised and require expensive manual annotation of large datasets. These problems are addressed here through the development of a more generic framework, incorporating advances in representation learning which allows for more flexibility in analysing new categories of imagery with limited labeled data. First, a robust representation of an unlabeled aerial imagery dataset was created based on the momentum …
Visual context is important in object recognition and it is still an open problem in computer vision. Along with the advent of deep convolutional neural networks (CNN), using contextual information with such systems starts to receive attention in the literature. At the same time, aerial imagery is gaining momentum. While advances in deep learning make good progress in aerial image analysis, this problem still poses many great challenges. Aerial images are often taken under poor lighting conditions and contain low resolution objects, many times occluded by trees or taller buildings. In this dom…
UAV-Rain1k: A Benchmark for Raindrop Removal from UAV Aerial Imagery
Shenyang Aerospace University（沈阳航空航天大学）；Naval Aviation University（海军航空大学）；Nanjing University of Science and Technology（南京理工大学）；Zhejiang Ocean University（浙江海洋大学）
Microsoft AI for Good Research Lab（微软人工智能公益研究实验室）；Stanford RegLab（斯坦福监管实验室）
Concentrated Animal Feeding Operations (CAFOs) pose serious risks to air, water, and public health, but have proven to be challenging to regulate. The U.S. Government Accountability Office notes that a basic challenge is the lack of comprehensive location information on CAFOs. We use the USDA's National Agricultural Imagery Program (NAIP) 1m/pixel aerial imagery to detect poultry CAFOs across the continental United States. We train convolutional neural network (CNN) models to identify individual poultry barns and apply the best performing model to over 42 TB of imagery to create the first nati…
Unmanned aerial vehicles now make it possible to obtain high quality aerial imagery at a low cost, but processing those images into a single, useful entity is neither simple nor seamless. Specifically, there are factors that must be addressed when merging multiple images into a single coherent one. While ortho-rectification can be done, it tends to be expensive and time consuming. Image stitching offers a more economical, low-tech approach. However direct application tends to fail for low-elevation imagery due to one or more factors including insufficient keypoints, parallax issues, and homoge…
State Key Lab. LIESMARS, Wuhan University（武汉大学测绘遥感信息工程国家重点实验室）；School of Automation, Northwestern Polytechnical University（西北工业大学自动化学院）
Given an aerial image, aerial scene parsing (ASP) targets to interpret the semantic structure of the image content, e.g., by assigning a semantic label to every pixel of the image. With the popularization of data-driven methods, the past decades have witnessed promising progress on ASP by approaching the problem with the schemes of tile-level scene classification or segmentation-based image analysis, when using high-resolution aerial images. However, the former scheme often produces results with tile-wise boundaries, while the latter one needs to handle the complex modeling process from pixels…
Evaluating the Efficacy of Sentinel-2 versus Aerial Imagery in Serrated Tussock Classification
School of Information Technology, Deakin University, Australia（信息技术学院，德堪大学，澳大利亚）；Agriculture Victoria Research, Department of Energy, Environment and Climate Action, Australia（维多利亚农业研究，能源、环境与气候变化行动部，澳大利亚）；Institute of Innovation, Science and Sustainability, Federation University, Australia（创新、科学与可持续性研究所，联邦大学，澳大利亚）
RareSpot+: A Benchmark, Model, and Active Learning Framework for Small and Rare Wildlife in Aerial Imagery
University of California, Santa Barbara（加州大学圣芭芭拉分校）；Smithsonian National Zoo and Conservation Biology Institute（史密森尼国家动物园与保护生物学研究所）；Stanford University（斯坦福大学）；The Doris Duke Foundation（多里斯·杜克基金会）
This paper proposes a novel domain adaptation algorithm to handle the challenges posed by the satellite and aerial imagery, and demonstrates its effectiveness on the built-up region segmentation problem. Built-up area estimation is an important component in understanding the human impact on the environment, the effect of public policy, and general urban population analysis. The diverse nature of aerial and satellite imagery and lack of labeled data covering this diversity makes machine learning algorithms difficult to generalize for such tasks, especially across multiple domains. On the other …
Cross-Domain Dead Tree Detection via Knowledge Distillation in Aerial Imagery
CSC – IT Center for Science Ltd.（CSC信息科技研究中心有限公司）；Department of Forest Sciences, University of Helsinki（赫尔辛基大学森林科学系）；KOKO Forest Ltd.（KOKO森林有限公司）；School of Forest Sciences, University of Eastern Finland（东芬兰大学森林科学学院）
In spite of the many advantages of aerial imagery for crowd monitoring and management at mass events, datasets of aerial images of crowds are still lacking in the field. As a remedy, in this work we introduce a novel crowd dataset, the DLR Aerial Crowd Dataset (DLR-ACD), which is composed of 33 large aerial images acquired from 16 flight campaigns over mass events with 226,291 persons annotated. To the best of our knowledge, DLR-ACD is the first aerial crowd dataset and will be released publicly. To tackle the problem of accurate crowd counting and density map estimation in aerial images of cr…
ReforesTree: A Dataset for Estimating Tropical Forest Carbon Stock with Deep Learning and Aerial Imagery
Technical University of Munich（慕尼黑工业大学）；ETH Zurich（苏黎世联邦理工学院）；Massachusetts Institute of Technology（麻省理工学院）；University of Warwick（华威大学）；New York University（纽约大学）；WWF Switzerland（世界自然基金会瑞士分会）
An Efficient Additive Kolmogorov-Arnold Transformer for Point-Level Maize Localization in Unmanned Aerial Vehicle Imagery
Department of Biological Systems Engineering, University of Wisconsin-Madison, Madison, WI 53706, USA（生物系统工程系，威斯康星大学麦迪逊分校）；Department of Agronomy, University of Wisconsin-Madison, Madison, WI 53706, USA（农学系，威斯康星大学麦迪逊分校）
University of Manouba（马努巴大学）；Taibah University（塔伊巴大学）；Prince Sultan University（苏丹王子大学）；Arab Open University（阿拉伯开放大学）；University of Sfax（斯法克斯大学）
Recently, Convolutional Neural Networks (CNNs) have made a great performance for remote sensing image classification. Plant recognition using CNNs is one of the active deep learning research topics due to its added-value in different related fields, especially environmental conservation and natural areas preservation. Automatic recognition of plants in protected areas helps in the surveillance process of these zones and ensures the sustainability of their ecosystems. In this work, we propose an Enhanced Randomly Initialized Convolutional Neural Network (ERI-CNN) for the recognition of columnar…
KASIKORN Labs（开泰实验室）；KASIKORN Business-Technology Group（开泰商业科技集团）；Korea Advanced Institute of Science and Technology（韩国科学技术院）；Chulalongkorn University（朱拉隆功大学）
Real estate is a critical sector in Thailand's economy, which has led to a growing demand for a more accurate land price prediction approach. Traditional methods of land price prediction, such as the weighted quality score (WQS), are limited due to their reliance on subjective criteria and their lack of consideration for spatial variables. In this study, we utilize aerial or satellite imageries from Google Map API to enhance land price prediction models from the dataset provided by Kasikorn Business Technology Group (KBTG). We propose a similarity-based asset valuation model that uses a Siames…
Multimodal Mathematical Reasoning Embedded in Aerial Vehicle Imagery: Benchmarking, Analysis, and Exploration
Department of Physics, J.K. Institute of Science（J.K.科学研究院物理系）；World Scientific University（世界科学大学）；University of Intelligent Studies（智能研究大学）；East China Normal University（华东师范大学）；Nanyang Technological University（南洋理工大学）；SenseTime Research（商汤科技研究院）；Shanghai Jiao Tong University（上海交通大学）；Harbin Institute of Technology（哈尔滨工业大学）
FLAME 3 Dataset: Unleashing the Power of Radiometric Thermal UAV Imagery for Wildfire Management
Holcombe Department of Electrical and Computer Engineering, Clemson University（克莱姆森大学霍尔科姆电气与计算机工程系）；Pacific Southwest Research Station, U.S. Forest Services（美国林业局太平洋西南研究站）；School of Environmental and Forest Sciences, University of Washington（华盛顿大学环境与森林科学学院）；US Forest Service, Rocky Mountain Research Station, Fire Sciences Laboratory（美国林业局落基山研究站火灾科学实验室）；Department of Mechanical Engineering, Clemson University（克莱姆森大学机械工程系）；Department of Forest Management, University of Montana（蒙大拿大学森林管理系）
Despite the breakthrough deep learning performances achieved for automatic object detection, small target detection is still a challenging problem, especially when looking at fast and accurate solutions suitable for mobile or edge applications. In this work we present YOLO-S, a simple, fast and efficient network for small target detection. The architecture exploits a small feature extractor based on Darknet20, as well as skip connection, via both bypass and concatenation, and reshape-passthrough layer to alleviate the vanishing gradient problem, promote feature reuse across network and combine…
Northern Arizona University（北亚利桑那大学）；Air Force Research Laboratory（美国空军研究实验室）
Wildfires are one of the costliest and deadliest natural disasters in the US, causing damage to millions of hectares of forest resources and threatening the lives of people and animals. Of particular importance are risks to firefighters and operational forces, which highlights the need for leveraging technology to minimize danger to people and property. FLAME (Fire Luminosity Airborne-based Machine learning Evaluation) offers a dataset of aerial images of fires along with methods for fire detection and segmentation which can help firefighters and researchers to develop optimal fire management …
KeyW Corp.（KeyW公司）；Sensors Directorate, Air Force Research Lab（空军研究实验室传感器处）
In recent years, several real-time or near real-time object detectors have been developed. However these object detectors are typically designed for first-person view images where the subject is large in the image and do not directly apply well to detecting vehicles in aerial imagery. Though some detectors have been developed for aerial imagery, these are either slow or do not handle multi-scale imagery very well. Here the popular YOLOv2 detector is modified to vastly improve it's performance on aerial data. The modified detector is compared to Faster RCNN on several aerial imagery datasets. T…
The University of Adelaide（阿德莱德大学）；University of South Australia（南澳大学）
Deep neural networks (DNNs) have become essential for processing the vast amounts of aerial imagery collected using earth-observing satellite platforms. However, DNNs are vulnerable towards adversarial examples, and it is expected that this weakness also plagues DNNs for aerial imagery. In this work, we demonstrate one of the first efforts on physical adversarial attacks on aerial imagery, whereby adversarial patches were optimised, fabricated and installed on or near target objects (cars) to significantly reduce the efficacy of an object detector applied on overhead images. Physical adversari…
We introduce a novel strategy for learning to extract semantically meaningful features from aerial imagery. Instead of manually labeling the aerial imagery, we propose to predict (noisy) semantic features automatically extracted from co-located ground imagery. Our network architecture takes an aerial image as input, extracts features using a convolutional neural network, and then applies an adaptive transformation to map these features into the ground-level perspective. We use an end-to-end learning approach to minimize the difference between the semantic segmentation extracted directly from t…
Raisa Energy LLC；Faculty of Engineering, Cairo University（开罗大学工程学院）；Faculty of Computers and Information, Cairo University（开罗大学计算机与信息学院）
Automation of objects labeling in aerial imagery is a computer vision task with numerous practical applications. Fields like energy exploration require an automated method to process a continuous stream of imagery on a daily basis. In this paper we propose a pipeline to tackle this problem using a stack of convolutional neural networks (U-Net architecture) arranged end-to-end. Each network works as post-processor to the previous one. Our model outperforms current state-of-the-art on two different datasets: Inria Aerial Image Labeling dataset and Massachusetts Buildings dataset each with differ…
Eindhoven University of Technology（埃因霍温理工大学）；Cyclomedia B.V（Cyclomedia公司）
Detection of buildings and other objects from aerial images has various applications in urban planning and map making. Automated building detection from aerial imagery is a challenging task, as it is prone to varying lighting conditions, shadows and occlusions. Convolutional Neural Networks (CNNs) are robust against some of these variations, although they fail to distinguish easy and difficult examples. We train a detection algorithm from RGB-D images to obtain a segmented mask by using the CNN architecture DenseNet.First, we improve the performance of the model by applying a statistical re-sa…
Nowadays, with the rapid development of consumer Unmanned Aerial Vehicles (UAVs), visual surveillance by utilizing the UAV platform has been very attractive. Most of the research works for UAV captured visual data are mainly focused on the tasks of object detection and tracking. However, limited attention has been paid to the task of person Re-identification (ReID) which has been widely studied in ordinary surveillance cameras with fixed emplacements. In this paper, to facilitate the research of person ReID in aerial imagery, we collect a large scale airborne person ReID dataset named as Perso…
Unmanned Aerial vehicles (UAV) are a promising technology for smart farming related applications. Aerial monitoring of agriculture farms with UAV enables key decision-making pertaining to crop monitoring. Advancements in deep learning techniques have further enhanced the precision and reliability of aerial imagery based analysis. The capabilities to mount various kinds of sensors (RGB, spectral cameras) on UAV allows remote crop analysis applications such as vegetation classification and segmentation, crop counting, yield monitoring and prediction, crop mapping, weed detection, disease and nut…
Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
Object detection in natural images has achieved remarkable results over the years. However, a similar progress has not yet been observed in aerial object detection due to several challenges, such as high resolution images, instances scale variation, class imbalance etc. We show the performance of two-stage, one-stage and attention based object detectors on the iSAID dataset. Furthermore, we describe some modifications and analysis performed for different models - a) In two stage detector: introduced weighted attention based FPN, class balanced sampler and density prediction head. b) In one sta…
German Aerospace Center (DLR)（德国航空航天中心（DLR））；Technical University of Munich（慕尼黑工业大学）
The knowledge about the placement and appearance of lane markings is a prerequisite for the creation of maps with high precision, necessary for autonomous driving, infrastructure monitoring, lane-wise traffic management, and urban planning. Lane markings are one of the important components of such maps. Lane markings convey the rules of roads to drivers. While these rules are learned by humans, an autonomous driving vehicle should be taught to learn them to localize itself. Therefore, accurate and reliable lane marking semantic segmentation in the imagery of roads and highways is needed to ach…
University of Kentucky（肯塔基大学）；University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）
We propose to use deep convolutional neural networks to address the problem of cross-view image geolocalization, in which the geolocation of a ground-level query image is estimated by matching to georeferenced aerial images. We use state-of-the-art feature representations for ground-level images and introduce a cross-view training approach for learning a joint semantic feature representation for aerial images. We also propose a network architecture that fuses features extracted from aerial images at multiple spatial scales. To support training these networks, we introduce a massive database th…
Building extraction from aerial images has several applications in problems such as urban planning, change detection, and disaster management. With the increasing availability of data, Convolutional Neural Networks (CNNs) for semantic segmentation of remote sensing imagery has improved significantly in recent years. However, convolutions operate in local neighborhoods and fail to capture non-local features that are essential in semantic understanding of aerial images. In this work, we propose to improve building segmentation of different sizes by capturing long-range dependencies using context…
German Aerospace Center (DLR)（德国航空航天中心（DLR））；Technical University of Munich（慕尼黑工业大学）
Multi-class vehicle detection from airborne imagery with orientation estimation is an important task in the near and remote vision domains with applications in traffic monitoring and disaster management. In the last decade, we have witnessed significant progress in object detection in ground imagery, but it is still in its infancy in airborne imagery, mostly due to the scarcity of diverse and large-scale datasets. Despite being a useful tool for different applications, current airborne datasets only partially reflect the challenges of real-world scenarios. To address this issue, we introduce E…
We consider the problem of automatically detecting small-scale solar photovoltaic arrays for behind-the-meter energy resource assessment in high resolution aerial imagery. Such algorithms offer a faster and more cost-effective solution to collecting information on distributed solar photovoltaic (PV) arrays, such as their location, capacity, and generated energy. The surface area of PV arrays, a characteristic which can be estimated from aerial imagery, provides an important proxy for array capacity and energy generation. In this work, we employ a state-of-the-art convolutional neural network a…
MARTIAN: A Rendering Framework for Aerial Mars Imagery from HiRISE Orbital Data
Space Robotics Research Group, SnT, University of Luxembourg（卢森堡大学空间机器人研究组）；Jet Propulsion Laboratory, California Institute of Technology（加州理工学院喷气推进实验室）
The trend towards higher resolution remote sensing imagery facilitates a transition from land-use classification to object-level scene understanding. Rather than relying purely on spectral content, appearance-based image features come into play. In this work, deep convolutional neural networks (CNNs) are applied to semantic labelling of high-resolution remote sensing data. Recent advances in fully convolutional networks (FCNs) are adapted to overhead data and shown to be as effective as in other domains. A full-resolution labelling is inferred using a deep FCN with no downsampling, obviating t…
Detection of pedestrians in aerial imagery captured by drones has many applications including intersection monitoring, patrolling, and surveillance, to name a few. However, the problem is involved due to continuouslychanging camera viewpoint and object appearance as well as the need for lightweight algorithms to run on on-board embedded systems. To address this issue, the paper proposes a framework for pedestrian detection in videos based on the YOLO object detection network [6] while having a high throughput of more than 5 FPS on the Jetson TX2 embedded board. The framework exploits deep lear…
