Bird's Eye View Research Articles

A Bird's‐Eye View of Animals in the Law

The article develops an analytic account of nonhuman animals’ current legal status. Animals are often characterised as legal things and property, but this characterisation is both simplistic and, in some cases, incorrect. The article seeks to dispel a number of orthodoxies regarding the legal status of animals and offer a more nuanced and contextual account. The emphasis is on Western law, with a particular focus on European jurisdictions. The article approaches animal legal status in terms of two historical regimes: the Commodity Regime and the More‐than‐Commodity Regime. While treating animals as commodities has been the rule for millennia, the situation has recently become more multifaceted. For instance, the private law status of companion animals has shifted away from that of commodities. Furthermore, it is argued that some wild animals have stopped being legal things altogether as a result of EU wildlife law. The multifarious arguments are then synthesised in order to produce a bird's‐eye view of animals in the law.

A bird's-eye view: exploration of the flavin-containing monooxygenase superfamily in common wheat.

The Flavin Monooxygenase (FMO) gene superfamily in plants is involved in various processes most widely documented for its involvement in auxin biosynthesis, specialized metabolite biosynthesis, and plant microbial defense signaling. The roles of FMOs in defense signaling and disease resistance have recently come into focus as they may present opportunities to increase immune responses in plants including leading to systemic acquired resistance, but are not well characterized. We present a comprehensive catalogue of FMOs found in genomes across vascular plants and explore, in depth, 170 wheat TaFMO genes for sequence architecture, cis-acting regulatory elements, and changes due to Transposable Element insertions. A molecular phylogeny separates TaFMOs into three clades (A, B, and C) for which we further report gene duplication patterns, and differential rates of homoeologue expansion and retention among TaFMO subclades. We discuss Clade B TaFMOs where gene expansion is similarly seen in other cereal genomes. Transcriptome data from various studies point towards involvement of subclade B2 TaFMOs in disease responses against both biotrophic and necrotrophic pathogens, substantiated by promoter element analysis. We hypothesize that certain TaFMOs are responsive to both abiotic and biotic stresses, providing potential targets for enhancing disease resistance, plant yield and other important agronomic traits. Altogether, FMOs in wheat and other crop plants present an untapped resource to be exploited for improving the quality of crops.

Reimagining our futures together: An early bird's‐eye view of inclusive organizational behavior

SummaryThe world has witnessed high‐intensity and low‐occurrence crises such as the COVID‐19 pandemic that have radically changed not only the discourses of health and safety but also permanently changed the realities of the workplace. The COVID‐19 pandemic‐related new normal has resulted in the exponential increase in the acceptance of “homeplace” or “work from home” in work‐related domains. With this sudden dramatic shift in the way the present and future work is being conceptualized, there is every reason to believe that employees struggle with a plethora of intertwined thoughts and emotions, particularly a heightened sense of social isolation and exclusion from their work environment. The present study is an attempt to address this concern in the broader ambit of inclusive organizational behavior. Using an interpretivist research approach, we dwell on the genesis of organizational behavior in changing times, particularly digitalization and social isolation. We employ inductive analysis of the employee data generated over two waves and use grounded theory to explain how inclusive behavior could be fostered within organizations. Our study provides an early conceptualization of inclusive organizational behavior by identifying four factors, namely, inclusive support, inclusive work design, inclusive culture, and inclusive mindset. Furthermore, based on the findings of the study, a three‐tier model of inclusive organizational behavior is proposed that links individual, group, and system‐level dynamics in the organizations.

A method for estimating ship berthing angle based on 2D bird's eye view point cloud

The accurate estimation of berthing angle is essential for the parallel berthing of inshore ships. Herein, a new method for calculating the ship berthing angle using a shore-based LiDAR system is proposed. First, the LiDAR-scanned point cloud data is preprocessed, including coordinate conversion, noise filtering, and data downsampling. Then, the processed point cloud data is projected onto a two-dimensional (2D) plane, and the height value is used as the pixel value to generate bird's eye view (BEV) images. Finally, an improved Hough transform is proposed to detect the straight line representing the ship's nearshore profile in the BEV images and replace the ship midline with the detected line for calculating the berthing angle. The performance of the proposed method is verified by applying it on simulated and real ship data. Simulation experiment results show that the maximum absolute error of our method is only 0.151°. Real ship experiments were conducted at Dalian Port (China) to verify the reliability and stability of the method compared with other berthing angle estimation methods and the compass equipment. Overall, the proposed method can effectively obtain the berthing angle of ships, assist in parallel berthing, and improve berthing efficiency.

Soil prokaryotic and fungal biome structures associated with crop disease status across the Japan Archipelago.

Archaea, bacteria, and fungi in the soil are increasingly recognized as determinants of agricultural productivity and sustainability. A crucial step for exploring soil microbiomes with important ecosystem functions is to perform statistical analyses on the potential relationship between microbiome structure and functions based on comparisons of hundreds or thousands of environmental samples collected across broad geographic ranges. In this study, we integrated agricultural field metadata with microbial community analyses by targeting 2,903 bulk soil samples collected along a latitudinal gradient from cool-temperate to subtropical regions in Japan (26.1-42.8 °N). The data involving 632 archaeal, 26,868 bacterial, and 4,889 fungal operational taxonomic units detected across the fields of 19 crop plant species allowed us to conduct statistical analyses (permutational analyses of variance, generalized linear mixed models, randomization analyses, and network analyses) on the relationship among edaphic factors, microbiome compositions, and crop disease prevalence. We then examined whether the diverse microbes form species sets varying in potential ecological impacts on crop plants. A network analysis suggested that the observed prokaryotes and fungi were classified into several species sets (network modules), which differed substantially in association with crop disease prevalence. Within the network of microbe-to-microbe coexistence, ecologically diverse microbes, such as an ammonium-oxidizing archaeon, an antibiotics-producing bacterium, and a potentially mycoparasitic fungus, were inferred to play key roles in shifts between crop-disease-promotive and crop-disease-suppressive states of soil microbiomes. The bird's-eye view of soil microbiome structure will provide a basis for designing and managing agroecosystems with high disease-suppressive functions.IMPORTANCEUnderstanding how microbiome structure and functions are organized in soil ecosystems is one of the major challenges in both basic ecology and applied microbiology. Given the ongoing worldwide degradation of agroecosystems, building frameworks for exploring structural diversity and functional profiles of soil microbiomes is an essential task. Our study provides an overview of cropland microbiome states in light of potential crop-disease-suppressive functions. The large data set allowed us to explore highly functional species sets that may be stably managed in agroecosystems. Furthermore, an analysis of network architecture highlighted species that are potentially used to cause shifts from disease-prevalent states of agroecosystems to disease-suppressive states. By extending the approach of comparative analyses toward broader geographic ranges and diverse agricultural practices, agroecosystem with maximized biological functions will be further explored.

Delving Into the Devils of Bird's-Eye-View Perception: A Review, Evaluation and Recipe.

Learning powerful representations in bird's-eye-view (BEV) for perception tasks is trending and drawing extensive attention both from industry and academia. Conventional approaches for most autonomous driving algorithms perform detection, segmentation, tracking, etc., in a front or perspective view. As sensor configurations get more complex, integrating multi-source information from different sensors and representing features in a unified view come of vital importance. BEV perception inherits several advantages, as representing surrounding scenes in BEV is intuitive and fusion-friendly; and representing objects in BEV is most desirable for subsequent modules as in planning and/or control. The core problems for BEV perception lie in (a) how to reconstruct the lost 3D information via view transformation from perspective view to BEV; (b) how to acquire ground truth annotations in BEV grid; (c) how to formulate the pipeline to incorporate features from different sources and views; and (d) how to adapt and generalize algorithms as sensor configurations vary across different scenarios. In this survey, we review the most recent works on BEV perception and provide an in-depth analysis of different solutions. Moreover, several systematic designs of BEV approach from the industry are depicted as well. Furthermore, we introduce a full suite of practical guidebook to improve the performance of BEV perception tasks, including camera, LiDAR and fusion inputs. At last, we point out the future research directions in this area. We hope this report will shed some light on the community and encourage more research effort on BEV perception.

A Birds Eye View History of Goa through Pilar Museum.

A Birds Eye View History of Goa through Pilar Museum.

Self-Supervised Bird’s Eye View Motion Prediction with Cross-Modality Signals

Learning the dense bird's eye view (BEV) motion flow in a self-supervised manner is an emerging research for robotics and autonomous driving. Current self-supervised methods mainly rely on point correspondences between point clouds, which may introduce the problems of fake flow and inconsistency, hindering the model’s ability to learn accurate and realistic motion. In this paper, we introduce a novel cross-modality self-supervised training framework that effectively addresses these issues by leveraging multi-modality data to obtain supervision signals. We design three innovative supervision signals to preserve the inherent properties of scene motion, including the masked Chamfer distance loss, the piecewise rigidity loss, and the temporal consistency loss. Through extensive experiments, we demonstrate that our proposed self-supervised framework outperforms all previous self-supervision methods for the motion prediction task.

Instance-Aware Multi-Camera 3D Object Detection with Structural Priors Mining and Self-Boosting Learning

Camera-based bird-eye-view (BEV) perception paradigm has made significant progress in the autonomous driving field. Under such a paradigm, accurate BEV representation construction relies on reliable depth estimation for multi-camera images. However, existing approaches exhaustively predict depths for every pixel without prioritizing objects, which are precisely the entities requiring detection in the 3D space. To this end, we propose IA-BEV, which integrates image-plane instance awareness into the depth estimation process within a BEV-based detector. First, a category-specific structural priors mining approach is proposed for enhancing the efficacy of monocular depth generation. Besides, a self-boosting learning strategy is further proposed to encourage the model to place more emphasis on challenging objects in computation-expensive temporal stereo matching. Together they provide advanced depth estimation results for high-quality BEV features construction, benefiting the ultimate 3D detection. The proposed method achieves state-of-the-art performances on the challenging nuScenes benchmark, and extensive experimental results demonstrate the effectiveness of our designs.

CMDA: Cross-Modal and Domain Adversarial Adaptation for LiDAR-Based 3D Object Detection

Recent LiDAR-based 3D Object Detection (3DOD) methods show promising results, but they often do not generalize well to target domains outside the source (or training) data distribution. To reduce such domain gaps and thus to make 3DOD models more generalizable, we introduce a novel unsupervised domain adaptation (UDA) method, called CMDA, which (i) leverages visual semantic cues from an image modality (i.e., camera images) as an effective semantic bridge to close the domain gap in the cross-modal Bird's Eye View (BEV) representations. Further, (ii) we also introduce a self-training-based learning strategy, wherein a model is adversarially trained to generate domain-invariant features, which disrupt the discrimination of whether a feature instance comes from a source or an unseen target domain. Overall, our CMDA framework guides the 3DOD model to generate highly informative and domain-adaptive features for novel data distributions. In our extensive experiments with large-scale benchmarks, such as nuScenes, Waymo, and KITTI, those mentioned above provide significant performance gains for UDA tasks, achieving state-of-the-art performance.

SOGDet: Semantic-Occupancy Guided Multi-View 3D Object Detection

In the field of autonomous driving, accurate and comprehensive perception of the 3D environment is crucial. Bird's Eye View (BEV) based methods have emerged as a promising solution for 3D object detection using multi-view images as input. However, existing 3D object detection methods often ignore the physical context in the environment, such as sidewalk and vegetation, resulting in sub-optimal performance. In this paper, we propose a novel approach called SOGDet (Semantic-Occupancy Guided Multi-view 3D Object Detection), that leverages a 3D semantic-occupancy branch to improve the accuracy of 3D object detection. In particular, the physical context modeled by semantic occupancy helps the detector to perceive the scenes in a more holistic view. Our SOGDet is flexible to use and can be seamlessly integrated with most existing BEV-based methods. To evaluate its effectiveness, we apply this approach to several state-of-the-art baselines and conduct extensive experiments on the exclusive nuScenes dataset. Our results show that SOGDet consistently enhance the performance of three baseline methods in terms of nuScenes Detection Score (NDS) and mean Average Precision (mAP). This indicates that the combination of 3D object detection and 3D semantic occupancy leads to a more comprehensive perception of the 3D environment, thereby aiding build more robust autonomous driving systems. The codes are available at: https://github.com/zhouqiu/SOGDet.

BEV-MAE: Bird’s Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving Scenarios

Existing LiDAR-based 3D object detection methods for autonomous driving scenarios mainly adopt the training-from-scratch paradigm. Unfortunately, this paradigm heavily relies on large-scale labeled data, whose collection can be expensive and time-consuming. Self-supervised pre-training is an effective and desirable way to alleviate this dependence on extensive annotated data. In this work, we present BEV-MAE, an efficient masked autoencoder pre-training framework for LiDAR-based 3D object detection in autonomous driving. Specifically, we propose a bird's eye view (BEV) guided masking strategy to guide the 3D encoder learning feature representation in a BEV perspective and avoid complex decoder design during pre-training. Furthermore, we introduce a learnable point token to maintain a consistent receptive field size of the 3D encoder with fine-tuning for masked point cloud inputs. Based on the property of outdoor point clouds in autonomous driving scenarios, i.e., the point clouds of distant objects are more sparse, we propose point density prediction to enable the 3D encoder to learn location information, which is essential for object detection. Experimental results show that BEV-MAE surpasses prior state-of-the-art self-supervised methods and achieves a favorably pre-training efficiency. Furthermore, based on TransFusion-L, BEV-MAE achieves new state-of-the-art LiDAR-based 3D object detection results, with 73.6 NDS and 69.6 mAP on the nuScenes benchmark. The source code will be released at https://github.com/VDIGPKU/BEV-MAE.

M-BEV: Masked BEV Perception for Robust Autonomous Driving

3D perception is a critical problem in autonomous driving. Recently, the Bird’s-Eye-View (BEV) approach has attracted extensive attention, due to low-cost deployment and desirable vision detection capacity. However, the existing models ignore a realistic scenario during the driving procedure, i.e., one or more view cameras may be failed, which largely deteriorates their performance. To tackle this problem, we propose a generic Masked BEV (M-BEV) perception framework, which can effectively improve robustness to this challenging scenario, by random masking and reconstructing camera views in the end-to-end training. More specifically, we develop a novel Masked View Reconstruction (MVR) module in our M-BEV. It mimics various missing cases by randomly masking features of different camera views, then leverages the original features of these views as self-supervision and reconstructs the masked ones with the distinct spatio-temporal context across camera views. Via such a plug-and-play MVR, our M-BEV is capable of learning the missing views from the resting ones, and thus well generalized for robust view recovery and accurate perception in the testing. We perform extensive experiments on the popular NuScenes benchmark, where our framework can significantly boost 3D perception performance of the state-of-the-art models on various missing view cases, e.g., for the absence of back view, our M-BEV promotes the PETRv2 model with 10.3% mAP gain.

RadOcc: Learning Cross-Modality Occupancy Knowledge through Rendering Assisted Distillation

3D occupancy prediction is an emerging task that aims to estimate the occupancy states and semantics of 3D scenes using multi-view images. However, image-based scene perception encounters significant challenges in achieving accurate prediction due to the absence of geometric priors. In this paper, we address this issue by exploring cross-modal knowledge distillation in this task, i.e., we leverage a stronger multi-modal model to guide the visual model during training. In practice, we observe that directly applying features or logits alignment, proposed and widely used in bird's-eye-view (BEV) perception, does not yield satisfactory results. To overcome this problem, we introduce RadOcc, a Rendering assisted distillation paradigm for 3D Occupancy prediction. By employing differentiable volume rendering, we generate depth and semantic maps in perspective views and propose two novel consistency criteria between the rendered outputs of teacher and student models. Specifically, the depth consistency loss aligns the termination distributions of the rendered rays, while the semantic consistency loss mimics the intra-segment similarity guided by vision foundation models (VLMs). Experimental results on the nuScenes dataset demonstrate the effectiveness of our proposed method in improving various 3D occupancy prediction approaches, e.g., our proposed methodology enhances our baseline by 2.2% in the metric of mIoU and achieves 50% in Occ3D benchmark.

Cross-Modal Match for Language Conditioned 3D Object Grounding

Language conditioned 3D object grounding aims to find the object within the 3D scene mentioned by natural language descriptions, which mainly depends on the matching between visual and natural language. Considerable improvement in grounding performance is achieved by improving the multimodal fusion mechanism or bridging the gap between detection and matching. However, several mismatches are ignored, i.e., mismatch in local visual representation and global sentence representation, and mismatch in visual space and corresponding label word space. In this paper, we propose crossmodal match for 3D grounding from mitigating these mismatches perspective. Specifically, to match local visual features with the global description sentence, we propose BEV (Bird’s-eye-view) based global information embedding module. It projects multiple object proposal features into the BEV and the relations of different objects are accessed by the visual transformer which can model both positions and features with long-range dependencies. To circumvent the mismatch in feature spaces of different modalities, we propose crossmodal consistency learning. It performs cross-modal consistency constraints to convert the visual feature space into the label word feature space resulting in easier matching. Besides, we introduce label distillation loss and global distillation loss to drive these matches learning in a distillation way. We evaluate our method in mainstream evaluation settings on three datasets, and the results demonstrate the effectiveness of the proposed method.

BEV-CFKT: A LiDAR-camera cross-modality-interaction fusion and knowledge transfer framework with transformer for BEV 3D object detection

The BEV-CFKT proposed in this paper leverages knowledge transfer through transformers for LiDAR-Camera fusion in the Bird’s-Eye-View (BEV) space, aiming to achieve accurate and robust 3D object detection. BEV-CFKT comprises three main components, which include the generation of BEV features from images and point clouds, cross-modality interaction, and hybrid object queries using a monocular detection head. By unifying features from both point clouds and images into the BEV space, we simplify modal interaction, facilitate knowledge transfer, and extract richer structural and semantic information from multimodal data. This effectively enhances the network’s performance. To further improve detection performance, BEV-CFKT incorporates a temporal fusion module. Additionally, a hybrid object queries module based on a monocular detection head accelerates the convergence of our model. We demonstrate the effectiveness of our approach through an extensive set of experiments.

A Curb-Detection Network with a Tri-Plane BEV Encoder Module for Autonomous Delivery Vehicles

Curb detection tasks play a crucial role in the perception of the autonomous driving environment for logistics vehicles. With the popularity of multi-modal sensors under the BEV (Bird’s Eye View) paradigm, curb detection tasks are increasingly being integrated into multi-task perception networks, achieving robust detection results. This paper modifies and integrates the tri-plane spatial feature representation method of the EG3D network from the field of 3D reconstruction into a BEV-based multi-modal sensor detection network, including LiDAR, pinhole cameras, and fisheye cameras. The system collects a total of 24,350 frames of data under real road conditions for experimentation, proving the effectiveness of the proposed method.

Three-Dimensional Point Cloud Object Detection Based on Feature Fusion and Enhancement

With the continuous emergence and development of 3D sensors in recent years, it has become increasingly convenient to collect point cloud data for 3D object detection tasks, such as the field of autonomous driving. But when using these existing methods, there are two problems that cannot be ignored: (1) The bird’s eye view (BEV) is a widely used method in 3D objective detection; however, the BEV usually compresses dimensions by combined height, dimension, and channels, which makes the process of feature extraction in feature fusion more difficult. (2) Light detection and ranging (LiDAR) has a much larger effective scanning depth, which causes the sector to become sparse in deep space and the uneven distribution of point cloud data. This results in few features in the distribution of neighboring points around the key points of interest. The following is the solution proposed in this paper: (1) This paper proposes multi-scale feature fusion composed of feature maps at different levels made of Deep Layer Aggregation (DLA) and a feature fusion module for the BEV. (2) A point completion network is used to improve the prediction results by completing the feature points inside the candidate boxes in the second stage, thereby strengthening their position features. Supervised contrastive learning is applied to enhance the segmentation results, improving the discrimination capability between the foreground and background. Experiments show these new additions can achieve improvements of 2.7%, 2.4%, and 2.5%, respectively, on KITTI easy, moderate, and hard tasks. Further ablation experiments show that each addition has promising improvement over the baseline.

A comprehensive research of deep learning approaches for High Definition map construction in autonomous driving

In the realm of autonomous driving, High Definition Maps (HD maps) are indispensable for safe and precise navigation. Traditional HD map construction methods involving point cloud capture and SLAM have proven effective but labor-intensive. This paper addresses the growing interest in leveraging deep learning techniques to streamline HD map creation. This paper presents a systematic exploration of deep learning methodologies for HD map construction. It categorizes these approaches into two core components: Feature Extraction and Feature Decoding. Feature Extraction involves the transformation of input data, comprising images and LiDAR point clouds, into Bird's Eye View (BEV) representations. Feature Decoding is dissected into rasterized map objectives and vector map objectives. Detailed analysis is conducted on prominent methodologies. The paper provides a nuanced evaluation of these deep learning techniques, highlighting their respective strengths and limitations. Factors such as precision, computational efficiency, and the preservation of fine-grained details are considered when selecting the most suitable method. This comprehensive review summarizes and prospects the research in related fields.

Learnable fusion mechanisms for multimodal object detection in autonomous vehicles

AbstractPerception systems in autonomous vehicles need to accurately detect and classify objects within their surrounding environments. Numerous types of sensors are deployed on these vehicles, and the combination of such multimodal data streams can significantly boost performance. The authors introduce a novel sensor fusion framework using deep convolutional neural networks. The framework employs both camera and LiDAR sensors in a multimodal, multiview configuration. The authors leverage both data types by introducing two new innovative fusion mechanisms: element‐wise multiplication and multimodal factorised bilinear pooling. The methods improve the bird's eye view moderate average precision score by +4.97% and +8.35% on the KITTI dataset when compared to traditional fusion operators like element‐wise addition and feature map concatenation. An in‐depth analysis of key design choices impacting performance, such as data augmentation, multi‐task learning, and convolutional architecture design is offered. The study aims to pave the way for the development of more robust multimodal machine vision systems. The authors conclude the paper with qualitative results, discussing both successful and problematic cases, along with potential ways to mitigate the latter.