Simple Scenes Research Articles

An examination of scene complexity’s role in cybersickness

This study explored the effects of scene complexity factor on cybersickness. In this between-subjects experiment, 44 participants played the Pendulum Chair VR game, half with a simple scene and half with a complex scene. The complex scene featured higher optic flow (lower-level perceptual factor) and higher familiarity (higher level factor). Dependent variables were cybersickness and task performance. Results were unexpected in that cybersickness did not differ significantly between the simple and complex scenes. These results suggest that the impact of optic flow and familiarity on cybersickness may be affected by each other or other factors, making them unreliable predictors of cybersickness if considered alone. Both lower level and higher-level factors would benefit from further research to deduce the conditions under which they affect cybersickness. VR designers could consider that optic flow and familiarity alone are not reliable factors when predicting the cybersickness-inducing effects of a new environment.

Multi-reference source aircraft classification network based on unknown class prototype estimation

Abstract Gathering complete aircraft types for close-set tasks is challenging and costly in fine-grained aircraft classification, resulting in encountering unknown class aircraft images in real-world models. To address this problem, we propose a network called a multi-reference source fine-grained aircraft classification network (MRSN) to explicitly and implicitly distinguish known class boundaries and embed unknown classes into the sample space. Specifically, we propose an embedding module (UCPE) to synthesize an unknown class prototype to facilitate the modeling of unknown class data distribution. Besides, we introduce a concatenated multi-reference source module (CMS) that combines distance measurement and probability estimation to classify whether testing images are of unknown class or not. Our proposed MRSN innovatively extends the open-set learning paradigm to the fine-grained classification of geospatial objects rather than simple scene classification. Besides, it shows excellent performance in our constructed dataset, which demonstrates the effectiveness and progressiveness of our method.

PSDF: Prior-Driven Neural Implicit Surface Learning for Multi-view Reconstruction.

Surface reconstruction has traditionally relied on the Multi-View Stereo (MVS)-based pipeline, which often suffers from noisy and incomplete geometry. This is due to that although MVS has been proven to be an effective way to recover the geometry of the scenes, especially for locally detailed areas with rich textures, it struggles to deal with areas with low texture and large variations of illumination where the photometric consistency is unreliable. Recently, Neural Implicit Surface Reconstruction (NISR) combines surface rendering and volume rendering techniques and bypasses the MVS as an intermediate step, which has emerged as a promising alternative to overcome the limitations of traditional pipelines. While NISR has shown impressive results on simple scenes, it remains challenging to recover delicate geometry from uncontrolled real-world scenes which is caused by its underconstrained optimization. To this end, the framework PSDF is proposed which resorts to external geometric priors from a pretrained MVS network and internal geometric priors inherent in the NISR model to facilitate high-quality neural implicit surface learning. Specifically, the visibility-aware feature consistency loss and depth prior-assisted sampling based on external geometric priors are introduced. These proposals provide powerfully geometric consistency constraints and aid in locating surface intersection points, thereby significantly improving the accuracy and delicate reconstruction of NISR. Meanwhile, the internal prior-guided importance rendering is presented to enhance the fidelity of the reconstructed surface mesh by mitigating the biased rendering issue in NISR. Extensive experiments on Tanks and Temples datasets show that PSDF achieves state-of-the-art performance on complex uncontrolled scenes.

From Simple to Complex Scenes: Learning Robust Feature Representations for Accurate Human Parsing.

Human parsing has attracted considerable research interest due to its broad potential applications in the computer vision community. In this paper, we explore several useful properties, including high-resolution representation, auxiliary guidance, and model robustness, which collectively contribute to a novel method for accurate human parsing in both simple and complex scenes. Starting from simple scenes: we propose the boundary-aware hybrid resolution network (BHRN), an advanced human parsing network. BHRN utilizes deconvolutional layers and multi-scale supervision to generate rich high-resolution representations. Additionally, it includes an edge perceiving branch designed to enhance the fineness of part boundaries. Building on BHRN, we construct a dual-task mutual learning (DTML) framework. It not only provides implicit guidance to assist the parser by incorporating boundary features, but also explicitly maintains the high-order consistency between the parsing prediction and the ground truth. Toward complex scenes: we develop a domain transform method to enhance the model robustness. By transforming the input space from the spatial domain to the polar harmonic Fourier moment domain, the mapping relationship to the output semantic space is highly stable. This transformation yields robust representations for both clean and corrupted data. When evaluated on standard benchmark datasets, our method achieves superior performance compared to state-of-the-art human parsing methods. Furthermore, our domain transform strategy significantly improves the robustness of DTML dramatically in most complex scenes.

Adaptive token selection for efficient detection transformer with dual teacher supervision

Recently DEtection TRansformer(DETR)-based models obtain remarkable performance in object detection and various foundational vision tasks. However, its performance is impeded by high computational demands since it exhibits quadratic scaling with the number of feature tokens. To mitigate redundant computations in some areas like the background, existing works propose static token selection methods, which choose a predefined portion of tokens to forward. However, it is intuitive that the complexity of inference for detection tasks varies depending on the input images. Static token selection methods rely on a fixed keeping ratio, causing performance degradation in complex scenes and inefficiency in simple scenes. To address this issue, we propose an Adaptive Token Selection method for DETR (ATS-DETR) that dynamically chooses the token keeping ratio based on the complexity of the input to retain the most salient tokens. To explicitly control the sparsity and improve the performance of ATS-DETR, we put forward a novel approach called Dual Teacher Supervision to train the ATS-DETR. Specifically, we utilize a weak teacher to assist the model in distinguishing input complexity and a strong teacher for enhancing overall model performance through feature distillation. We further introduce the Global Distillation to minish the disparities of the feature patterns extracted from ATS-DETR and the strong teacher model. Extensive experiments demonstrate that ATS-DETR attains better performance compared to Deformable DETR while achieving an 83% reduction of GFLOPs in the encoder, and outperforms all the static token selection methods.

Fungsi Dan Peran Media Masa Dalam Film Habibie Ainun (ANALISIS SEMIOTIKA Roland Barthes)

This study analyzes the semiotics of the role and function of mass media in Habibie Ainun's films. This story is taken from the real life of a young man named Baharudin Jusuf Habibie who tried to build the Indonesian aerospace industry and make airplanes. The purpose of this study is to find out how the moral message conveyed in Rudy Habibie's film shapes moral messages such as human relationships with others, God, and their social environment. Using the k approach Myths, on the other hand, explain the habits and beliefs of the general public. The study divides the scene into three parts: man's relationship with man, man's relationship with God, and man's relationship with the social environment. Each section consists of eleven simple scenes. Data collection identifies the corpus of subtitles according to the classification found. The results of the research can be shown by the existence of mass media through this film will have a good impact on the community, especially for teenagers who can be innovated towards the main character who is memorable to bring many examples of good moral values that can be applied in everyday life and at the same time can boost the life of a more advanced nation.

Using Auto-ML on Synthetic Point Cloud Generation

Automated Machine Learning (Auto-ML) has primarily been used to optimize network hyperparameters or post-processing parameters, while the most critical component for training a high-quality model, the dataset, is usually left untouched. In this paper, we introduce a novel approach that applies Auto-ML methods to the process of generating synthetic datasets for training machine learning models. Our approach addresses the problem that generating synthetic datasets requires a complex data generator, and that developing and tuning a data generator for a specific scenario is a time-consuming and expensive task. Being able to reuse this data generator for multiple purposes would greatly reduce the effort and cost, once the process of tuning it to the specific domains of each task is automated. To demonstrate the potential of this idea, we have implemented a point cloud generator for simple scenes. The scenes from this generator can be used to train a neural network to semantically segment cars from the background. The simple composition of the scene allows us to reuse the generator for several different semantic segmentation tasks. The models trained on the datasets with the optimized domain parameters easily outperform a model without such optimizations, while the optimization effort is minimal due to our Auto-ML approach. Although the development of such complex data generators requires considerable effort, we believe that using Auto-ML for dataset creation has the potential to speed up the development of machine learning applications in domains where high-quality labeled data is difficult to obtain.

Joint spatio-temporal modeling for visual tracking

Similarity-based approaches have made significant progress in visual object tracking (VOT). Although these methods work well in simple scenes, they ignore the continuous spatio-temporal connection of the object in the video sequence. For this reason, tracking by spatial matching solely can lead to tracking failures because of distractors and occlusion. In this paper, we propose a spatio-temporal joint-modeling tracker named STTrack which implicitly builds continuous connections between the temporal and spatial aspects of the sequence. Specifically, we first design a time-sequence iteration strategy (TSIS) to concentrate on the temporal connection of the object in the video sequence. Then, we propose a novel spatial temporal interaction Transformer network (STIN) to capture the spatio-temporal correlation of the object between frames. The proposed STIN module is robust in object occlusion because it explores the dynamic state change dependencies of the object. Finally, we introduce a spatio-temporal query to suppress distractors by iteratively propagating the target prior. Extensive experiments on six tracking benchmark datasets demonstrate that the proposed STTrack achieves excellent performance while operating in real-time. The code is publicly available at https://github.com/nubsym/STTrack.

RGB depth salient object detection via cross‐modal attention and boundary feature guidance

AbstractRGB depth (RGB‐D) salient object detection (SOD) is a meaningful and challenging task, which has achieved good detection performance in dealing with simple scenes using convolutional neural networks, however, it cannot effectively handle scenes with complex contours of salient objects or similarly coloured salient objects and background. A novel end‐to‐end framework is proposed for RGB‐D SOD, which comprises of four main components: the cross‐modal attention feature enhancement (CMAFE) module, the multi‐level contextual feature interaction (MLCFI) module, the boundary feature extraction (BFE) module, and the multi‐level boundary attention guidance (MLBAG) module. The CMAFE module retains the more effective salient features by employing a dual‐attention mechanism to filter noise from two modalities. In the MLCFI module, a shuffle operation is used for high‐level and low‐level channels to promote cross‐channel information communication, and rich semantic information is extracted. The BFE module converts salient features into boundary features to generate boundary maps. The MLBAG module produces saliency maps by aggregating multi‐level boundary saliency maps to guide cross‐modal features in the decode stage. Extensive experiments are conducted on six public benchmark datasets, with the results demonstrating that the proposed model significantly outperforms 23 state‐of‐the‐art RGB‐D SOD models with regards to multiple evaluation metrics.

Detection and Mapping of Chestnut Using Deep Learning from High-Resolution UAV-Based RGB Imagery

The semantic segmentation method based on high-resolution RGB images obtained by unmanned aerial vehicle (UAV) provides a cost-effective way to improve the accuracy of detection and classification in forestry. Few studies have explored the impact of sample distribution patterns on deep learning model detection accuracy. The study was carried out using the data from the 4.78 km2 RGB image of a chestnut (Castanea mollissima Blume) plantation obtained by the DJI Phantom 4-RTK, and the model training was conducted with 18,144 samples of manually delineated chestnut tree clusters. The performance of four semantic segmentation models (U-Net, DeepLab V3, PSPNet, and DeepLab V3+) paired with backbones (ResNet-34, ResNet-50) was evaluated. Then, the influence of chestnut data from different planting patterns on the accuracy and generalization performance of deep learning models was examined. The results showed that the combination of DeepLab V3 with ResNet-34 backbone gives the best performance (F1 score = 86.41%), while the combination of DeepLab V3+ with ResNet-50 backbone performed the worst. The influence of different backbone networks on the detection performance of semantic segmentation models did not show a clear pattern. Additionally, different spatial distribution patterns of chestnut planting affected the classification accuracy. The model MIX, trained on comprehensive training data, achieves higher classification accuracies (F1 score = 86.13%) compared to the model trained on single training data (F1 score (DP) = 82.46%; F1 score (SP) = 83.81%). The model performance in complex scenario data training is superior to that of the model in simple scene data training. In conclusion, comprehensive training databases can improve the generalization performance of chestnut classification with different spatial distribution patterns. This study provides an effective method for detecting chestnut cover area based on semantic segmentation, allowing for better quantitative evaluation of its resource utilization and further development of inventories for other tree species.

Heterogeneous group path planning algorithm based on data and mechanism model

AbstractIt is a challenging task to find a feasible path from the start to the end for heterogeneous group and avoid collision between dynamic agents and static obstacles. The existing methods are usually applicable to static simple scenes or the type of scenes including a single kind of agents, and it is difficult to meet the high dynamic heterogeneous group movements. To address the above issues, we propose a hybrid driven heterogeneous group path planning method based on data and mechanism model. Data and mechanism model are combined to drive movements of heterogeneous groups. The experimental results show that our method can describe movements of heterogeneous groups more realistically and solve the collision avoidance of heterogeneous groups well. We quantitatively evaluate our method using metrics such as the number of inflection points and the average turning angle. Average turning angle has decreased by 59.50% on average over prior methods. Number of inflection points has decreased by 69.19% on average over prior methods.

Precision of Memory for Attended and Ignored Colors

Selective attention can enhance some aspects of our visual world while filtering others from awareness. Given our limited cognitive resources, such filtering is essential when viewing complex scenes, but it also applies to simple scenes. Eitam, Yeshurun, and Hassan (2013) observed better performance for the attended color than the ignored color in a simple, two-colored object even though both colors were salient and the complexity of the display did not tax the capacity of visual memory. Our goal was to replicate this finding while addressing a potential task demand that could have contributed to the results. Specifically, participants might have misread the instructions and mistakenly reported the attended color when asked to report the ignored color first. Experiment 1 (n=67) replicated Eitam et al.’s (2013) finding while measuring memory precision. We found that people had worse memory for the ignored than the attended feature of a single, simple object. Experiment 2 (n=69) replicated the pattern while again addressing the potential task demand, although the effect was smaller. Experiment 3 (n=186) provided visual feedback to eliminate any remaining risk of response error and again replicated the original finding. Attended information was stored with greater precision than unattended information, even for a simple object.

RPP-Net: Rigid Constrained Point Cloud Prediction Network

Forecasting the future environment is an essential and fundamental capability of autonomous driving systems. In contrast to the widely studied video prediction, only a few literatures have explored LiDAR point cloud prediction. To achieve future point cloud generation, most existing methods are based on free-form 3D scene flow prediction. However, these simple scene flow prediction-based methods may cause distortions since the motions of 3D scenes can be seen as a combination of rigid (static background) and flow (dynamic foreground) motions. To address this issue, we propose a simple but effective rigid constrained point cloud prediction network named RPP-Net. The key component of the proposed method is the hybrid motion decoder, which generates motion masks and combines flow motions and rigid motions to produce hybrid motions without additional annotations and sensors. Besides, to reduce running time, we provide a hierarchical cell, which uses a feature encoder to extract deep features and an RPP-RNN module to capture temporal correlations across frames. To evaluate the effectiveness of our RPP-Net, we have conducted extensive experiments on both KITTI dataset and Argoverse dataset and the results show that our RPP-Net significantly outperforms existing methods and achieves a new state-of-the-art.

Research on 3D Reconstruction of Binocular Vision Based on Thermal Infrared.

Thermal infrared imaging is less affected by lighting conditions and smoke compared to visible light imaging. However, thermal infrared images often have lower resolution and lack rich texture details, making them unsuitable for stereo matching and 3D reconstruction. To enhance the quality of infrared stereo imaging, we propose an advanced stereo matching algorithm. Firstly, the images undergo preprocessing using a non-local mean noise reduction algorithm to remove thermal noise and achieve a smoother result. Subsequently, we perform camera calibration using a custom-made chessboard calibration board and Zhang's camera calibration method to obtain accurate camera parameters. Finally, the disparity map is generated using the SGBM (semi-global block matching) algorithm based on the weighted least squares method, enabling the 3D point cloud reconstruction of the object. The experimental results demonstrate that the proposed algorithm performs well in objects with sufficient thermal contrast and relatively simple scenes. The proposed algorithm reduces the average error value by 10.9 mm and the absolute value of the average error by 1.07% when compared with the traditional SGBM algorithm, resulting in improved stereo matching accuracy for thermal infrared imaging. While ensuring accuracy, our proposed algorithm achieves the stereo reconstruction of the object with a good visual effect, thereby holding high practical value.

A Re-detection Target Tracking Framework after Loss for Unmanned Aerial Vehicle

Currently, the target tracking algorithm based on discriminative correlation filter (DCF) and deep learning (DL) plays an increasingly important role in UAV (unmanned aerial vehicle). However, existing algorithms have limitations such as limited search region, difficulty in re-capturing targets when tracking is lost, and high computational complexity, which makes them difficult to apply to the UAV platform. In this paper, a target re-detection tracking algorithm (RDT) after tracking loss is designed for mobile platforms. RDT uses DCF in simple scenes to track targets and establish a target model between different frames. To ensure the algorithm when tracking is lost due to occlusion or moving out of view, an efficient switching criterion is designed to indirectly invoke the detection algorithm to re-capture the target and guide online learning of DCF. And the experiment results on the OTB benchmark show that RDT can re-capture the target after tracking is lost, and the speed of operation on the CPU is 85fps.

NeRSemble: Multi-view Radiance Field Reconstruction of Human Heads

We focus on reconstructing high-fidelity radiance fields of human heads, capturing their animations over time, and synthesizing re-renderings from novel viewpoints at arbitrary time steps. To this end, we propose a new multi-view capture setup composed of 16 calibrated machine vision cameras that record time-synchronized images at 7.1 MP resolution and 73 frames per second. With our setup, we collect a new dataset of over 4700 high-resolution, high-framerate sequences of more than 220 human heads, from which we introduce a new human head reconstruction benchmark 1 . The recorded sequences cover a wide range of facial dynamics, including head motions, natural expressions, emotions, and spoken language. In order to reconstruct high-fidelity human heads, we propose Dynamic Neural Radiance Fields using Hash Ensembles (NeRSemble). We represent scene dynamics by combining a deformation field and an ensemble of 3D multi-resolution hash encodings. The deformation field allows for precise modeling of simple scene movements, while the ensemble of hash encodings helps to represent complex dynamics. As a result, we obtain radiance field representations of human heads that capture motion over time and facilitate re-rendering of arbitrary novel viewpoints. In a series of experiments, we explore the design choices of our method and demonstrate that our approach outperforms state-of-the-art dynamic radiance field approaches by a significant margin.

Research on the Development Trend of Artificial Intelligence Led by ChatGPT

The technological growth of artificial intelligence (AI) generally presents the characteristics from simple linearity to complex system. In the early days of AI, its basic idea was simple imperative programming. However, people soon found that it could not complete complex thinking work and could only be used in simple scenes such as data processing, video games and industrial automatic control. ChatGPT, which was born, opened the era of universal AI, which indicates that AI has extensive learning ability and reaches or exceeds the level of ordinary human beings in most fields. ChatGPT, as a new generation of AI technology, will profoundly affect human economic and social development. In the future, AI will almost bring changes and reconstruction to all walks of life. Under the background of deepening the supply-side structural reform, it is of great significance to promote the practical application of AI and continuously provide new kinetic energy for economic development. This paper analyzes the development opportunities and challenges of ChatGPT in AI industry, labor and employment, education, scientific research and other fields, and explores the development trend of AI led by ChatGPT.

Boosting visual servoing performance through RGB-based methods

Purpose This paper aims to evaluate and compare the performance of different computer vision algorithms in the context of visual servoing for augmented robot perception and autonomy. Design/methodology/approach The authors evaluated and compared three different approaches: a feature-based approach, a hybrid approach and a machine-learning-based approach. To evaluate the performance of the approaches, experiments were conducted in a simulated environment using the PyBullet physics simulator. The experiments included different levels of complexity, including different numbers of distractors, varying lighting conditions and highly varied object geometry. Findings The experimental results showed that the machine-learning-based approach outperformed the other two approaches in terms of accuracy and robustness. The approach could detect and locate objects in complex scenes with high accuracy, even in the presence of distractors and varying lighting conditions. The hybrid approach showed promising results but was less robust to changes in lighting and object appearance. The feature-based approach performed well in simple scenes but struggled in more complex ones. Originality/value This paper sheds light on the superiority of a hybrid algorithm that incorporates a deep neural network in a feature detector for image-based visual servoing, which demonstrates stronger robustness in object detection and location against distractors and lighting conditions.

Exploring bias in the OCO-3 snapshot area mapping mode via geometry, surface, and aerosol effects

Abstract. The Atmospheric Carbon Observations from Space (ACOS) retrieval algorithm has been delivering operational column-averaged carbon dioxide dry-air mole fraction (XCO2​​​​​​​) data for the Orbiting Carbon Observatory (OCO) missions since 2014. The ACOS Level 2 Full Physics (L2FP) algorithm retrieves a number of parameters, including aerosol and surface properties, in addition to atmospheric CO2. Past analysis has shown that while the ACOS retrieval meets mission precision requirements of 0.1 %–0.5 % in XCO2, residual biases and some sources of error remain unaccounted for (Wunch et al., 2017; Worden et al., 2017; Torres et al., 2019). Forward model and other errors can lead to systematic biases in the retrieved XCO2, which are often correlated with these additional retrieved parameters. The characterization of such biases is particularly essential to urban- and local-scale emissions studies, where it is critical to accurately distinguish source signals relative to background concentrations (Nassar et al., 2017; Kiel et al., 2021). In this study we explore algorithm-induced biases through the use of simulated OCO-3 snapshot area mapping (SAM) mode observations, which offer a unique window into these biases with their wide range of viewing geometries over a given scene. We focus on a small percentage of SAMs in the OCO-3 vEarly product which contains artificially strong across-swath XCO2 biases spanning several parts per million, related to observation geometry. We investigate the causes of swath bias by using the timing and geometry of real OCO-3 SAMs to retrieve XCO2 from custom simulated Level 1b radiance spectra. By building relatively simple scenes and testing a variety of parameters, we find that aerosol is the primary driver of swath bias, with a complex combination of viewing geometry and aerosol optical properties contributing to the strength and pattern of the bias. Finally, we seek to understand successful mitigation of swath bias in the new OCO-3 version 10 data product. Results of this study may be useful in uncovering other remaining sources of XCO2 bias and may help minimize similar retrieval biases for both present missions (GOSAT, GOSAT-2, OCO-2, OCO-3, TanSat) and future missions (e.g., MicroCarb, GeoCarb, GOSAT-GW, CO2M).

SPN2D-GAN: Semantic Prior Based Night-to-Day Image-to-Image Translation

Existing image-to-image translation approaches can deal with simple scenes or styles effectively, such as summer-to-winter, horses-to-zebra, and photo-to-map. Although a great progress has been made by GAN-based methods recently, the performance of night-to-day (N2D) translation remains unsatisfactory due to imbalanced/poor visibility, and thus leading to translation ambiguity. To improve the quality of N2D translation, we propose an unpaired translation scheme based on a semantic prior generator, namely SPN2D-GAN, in a weakly-supervised manner with consideration of both image and semantic information. Specifically, we design a novel N2D generator, which can adopt the semantic information of images as prior knowledge to generate more reasonable and realistic results. Also, we suggest adjusting the brightness of nighttime images to boost the visibility, so that the generator can better extract content information. Moreover, the proposed SPN2D-GAN translates images by enforcing the distribution of daytime images in both image and semantic domains on final outputs. Besides, the cycle consistency is employed to preserve the fidelity between translations from two directions. Extensive experimental results are provided to reveal the effectiveness of our design, and demonstrate its superior performance over other state-of-the-art N2D translation approaches both quantitatively and qualitatively. Our code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/brightknight177/SPN2DGAN</uri> .