Comparative Study of Relative-Pose Estimations from a Monocular Image Sequence in Computer Vision and Photogrammetry †

Estimating motion parameters and spatial position of object is very important in target tracking and computer vision. The constraint for obtaining 3D motion and coordinates from a monocular image sequence is first presented and proved in this paper. With this constraint, a nonlinear recursive filtering algorithm for estimating 3D motion parameters and 3D spatial position of a point target from monocular images has been proposed. The performance of the proposed technique on simulated image sequence is also involved. Keywords: image analysis, motion estimation, recursive filtering

This survey provides a comprehensive overview of recent advancements and challenges in Artificial Intelligence (AI)‐enabled computer vision (CV) techniques for space robotic missions, spanning critical phases such as Entry, Descent, and Landing (EDL), orbital operations, and planetary surface exploration. Emphasis is placed on deep‐learning–based approaches for image classification, object detection, semantic segmentation, relative pose estimation, and feature matching. State‐of‐the‐art methods in terrain‐relative navigation, crater‐based or rock‐feature matching, and pose estimation for uncooperative targets are highlighted, illustrating the progress achieved through hybrid pipelines combining deep neural networks with classical geometry. The paper also critically evaluates publicly available orbital and planetary data sets—along with the increasing role of synthetic data—for developing and benchmarking CV algorithms under strict resource limitations and harsh environmental conditions. Despite demonstrated success in tasks like autonomous landing, debris removal, and rover navigation, current solutions face significant hurdles. These include computational constraints on onboard hardware, insufficient coverage of planetary conditions in existing data sets, and limited adaptability to dynamically changing environments. To address these shortcomings, research must prioritize lightweight neural architectures, advanced synthetic data generation, adaptive or incremental learning, and robust multisensor fusion. By integrating these strategies, AI‐based CV systems can advance autonomy, precision, and resilience in future space missions.

Today, computer vision has shown a variety of roles in our lives, making people’s life more convenient. Also, a variety of artificial intelligence models and algorithms have emerged for computer vision. Image matching is an important technique in the field of computer vision to find the similarities between two images or multiple images with the help of matching algorithms to achieve scientific and accurate processing of images. Therefore, summarizing the effective approximate solution to this problem as well as the future research is the main part for current research. The paper firstly describes the basic elements of the image matching technique. Then, some representative traditional image matching algorithms proposed in the field of computer vision research in recent years are summarized and reviewed. Finally, the future research directions and research ideas of image matching are discussed, providing reliable guidance and reference for subsequent research.

Human motion capture (MoCap) plays a key role in healthcare and human–robot collaboration. Some researchers have combined orientation measurements from inertial measurement units (IMUs) and positional inference from cameras to reconstruct the 3D human motion. Their works utilize multiple cameras or depth sensors to localize the human in three dimensions. Such multiple cameras are not always available in our daily life, but just a single camera attached in a smart IP devices has recently been popular. Therefore, we present a 3D pose estimation approach from IMUs and a single camera. In order to resolve the depth ambiguity of the single camera configuration and localize the global position of the subject, we present a constraint which optimizes the foot-ground contact points. The timing and 3D positions of the ground contact are calculated from the acceleration of IMUs on foot and geometric transformation of foot position detected on image, respectively. Since the results of pose estimation is greatly affected by the failure of the detection, we design the image-based constraints to handle the outliers of positional estimates. We evaluated the performance of our approach on public 3D human pose dataset. The experiments demonstrated that the proposed constraints contributed to improve the accuracy of pose estimation in single and multiple camera setting.

Human pose estimation is a pivotal domain within computer vision, underpinning applications from motion capture in cinematic production to sophisticated user interfaces in desktop devices. This research delineates the implementation of real-time human pose estimation within web browsers utilizing TensorFlow.js and the PoseNet model. PoseNet, an advanced machine learning model optimized for browser-based execution, facilitates precise pose detection sans specialized hardware. The primary aim of this study is to integrate PoseNet with TensorFlow.js, achieving efficient real-time pose estimation directly in the browser by leveraging JavaScript, thereby ensuring seamless user interaction and broad accessibility. A modular system architecture is designed, focusing on optimization strategies such as model quantization, asynchronous processing, and on-device computation to enhance performance and privacy preservation. In conclusion, this research establishes a robust framework for deploying PoseNet in web environments, underscoring its potential to revolutionize human-computer interaction within browser-based applications. Our findings contribute significantly to the field of computer vision and machine learning, offering insights into the practical deployment of pose estimation models on widely accessible platforms. Keywords — ReaReal-time Pose Estimation, TensorFlow.js, PoseNet, Machine Learning, Computer Vision, Browser-based Pose Detection, Human-Computer Interaction, Multi-person Tracking, On-device Computation, Asynchronous Processing, Cross-browser Compatibility, Performance Optimization, Privacy-preserving AI, Web-based Machine Learning, Motion Capture, Fitness Tracking, Interactive , Virtual Reality Interfaces, Deep LearningLearning

Разработано программное обеспечение ImgOpinion, которое позволяет выполнять оптико-структурный анализ цифрового изображения объекта методами компьютерного зрения. Оно предназначено для использования в экспертных лабораториях в составе аппаратно-программного комплекса компьютерного зрения MS-Unit, который включает специализированный осветитель “Фотобокс 3138” с цифровой регистрирующей камерой. Выходные данные строятся в виде цифрового паспорта огнестрельного повреждения, в котором приводятся криминалистически значимые характеристики объекта исследования, а также выявленных на нем следов выстрела. The ImgOpinion software, capable to perform the optical and structural analysis of a digital image of the object by computer vision methods, was developed. It can be employed in expert laboratories as a part of the computer vision hardware-software complex MS-Unit together with specialized illuminator “Photobox 3138” with a digital recording camera. The output data is constructed in the form of a digital passport of the gunshot residue, which contains forensically significant characteristics of the object under investigation, as well as a gunshot residue detected on it. Purpose. The research has solved the problem of creating a specialised hardware and software complex for forensic examination, the use of which partially automates the processes of identification and quantitative characterisation of gunshot traces and products. Methodology. Non-destructive research methods are implemented in computer vision systems, which include two main stages: a digital image acquisition and its mathematical processing. The hardware and software complex of a computer vision usually consists of an illuminator, a digital recording video camera and a specialised program for processing the raw data. Findings. ImgOpinion software has been developed, which allows performing the optical-structural analyses of digital images using the computer vision methods and is intended for use in expert laboratories as part of the MS-Unit computer vision hardware and software complex, which includes a specialized illuminator “Photobox 3138” with a digital recording camera. Autonomous and portable device has a mobile design and provides white light with colour temperature 5000 K (CIE D50) and colour rendering index CRI = 97+. Six independently switched LED monochrome illuminators with narrow spectral bands from 365 to 880 nm (UV to IR spectral bands) provide the uniform illumination without extraneous stray light on the working field (light intensity drop below 2 % at the edges of the working field). Value. The ImgOpinion output is constructed in the form of a digital passport of a gunshot injury, which contains forensically relevant characteristics of the object of investigation. The digital passport is an adaptation of the forensically significant information on the firearm traces for the integration into specialized databases for further development of the automation of expert evaluation processes, conducting the automated trace comparison and the determination of incident circumstances by it.

Optical accuracy is a primary driver of parabolic trough concentrating solar power (CSP) plant performance, but can be damaged by wind loads, gravity, error during installation, and regular plant operation. Collecting and analyzing optical measurements over an entire operating parabolic trough plant is difficult, given the large scale of typical installations. Distant Observer, a software tool developed at the National Renewable Energy Laboratory, uses images of the absorber tube reflected in the collector mirror to measure both surface slope in the parabolic mirror and offset of the absorber tube from the ideal focal point. This technology has been adapted for fast data collection using low-cost commercial drones, but until recently still required substantial human labor to process large amounts of data. A new method leveraging advanced deep learning and computer vision tools can drastically reduce the time required to process images. This new method addresses the primary analysis bottleneck, identifying featureless, reflective mirror corner points to a high degree of accuracy. Recent work has shown promising results using computer vision methods. The combined deep learning and computer vision approach presented here proved highly effective and has the potential to further automate data collection and analysis, making the tool more robust. The method presented in this paper automatically identified 74.3% of mirror corners within 2 pixels of their manually marked counterparts and 91.9% within 3 pixels. This level of accuracy is sufficient for practical Distant Observer analysis within a target uncertainty. A commercial drone collected video of over 100 parabolic trough modules at an operating CSP plant to demonstrate the deep learning and computer vision method’s usefulness in processing large amounts of data. These troughs were successfully analyzed using Distant Observer, paired with the new deep learning and computer vision algorithm, and can provide plant operators and trough designers with valuable insight about plant performance, operating strategies, and plant-wide optical error trends.

A novel estimation method for the 6 degree-of-freedom (6-DOF) motion of a target moving with slowly varying velocity is proposed, which is based on the monocular image sequences from a moving camera. The homography matrix for moving targets is derived. It is shown that the dynamic model of the target in 6-DOF motion can be described as a linear time-varying system. Consequently, the Kalman filter can be directly applied. Our estimation method does not need a priori information of target depth or size. The observability condition of our estimator is much milder than that of the previously known bearings-only tracking methods.

Automatic 3D model acquisition and 3D tracking of simple objects under motion using a single camera is often difficult due to the sparsity of information from which to establish the model. We have developed an automatic scheme that first computes a simple pointalistic Euclidean model of the object and then enriches this model using hyper-patches. These hyper-patches contain information on both the orientation and intensity pattern variation of roughly planar patches on an object. This information allows both the spatial and intensity distortions of the projected patch to be modelled accurately under 3D object motion. We show that hyper-patches not only can be computed automatically during model acquisition from a monocular image sequence, but that they are also extremely appropriate for the task of visual tracking.

Rapid-Motion-Track: Markerless tracking of fast human motion with deep learning

This paper is concerned with three-dimensional (3D) analysis of images showing 3D motion of an observer relative to a scene. It presents an approach to recovering 3D motion and structure parameters from multiple features present in a monocular image sequence such as points, regions, lines, texture gradient and vanishing line. For concreteness, the paper focuses on flight images of a planar, textured surface. In this paper, a linear integrated estimation method using two views is developed. Then, for robust estimation, a nonlinear integrated estimation method using multiple frames is presented. The integration of information in these diverse features is carried out using minimization of image errors. To reduce computation, a sequential-batch method is used to compute motion and structure. Performance is evaluated through simulations and experiments with a real image sequence digitized from a commercially available laserdisc of films taken from flying aircrafts.KeywordsImage SequenceImage ErrorTexture GradientDefense Advance Research Project AgencyMultiple FrameThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

This paper proposes a method to precisely estimate both the shape (link lengths) and pose (joint angles) of a articulated object from a monocular image sequence. Normal model-fitting method often leads to wrong estimates due to depth ambiguity in monocular views. The paper proposes a filtering method with constraint knowledge of the object represented as inequalities. The method calculates the probability distribution satisfying both the observation and the constraints. When multiple solutions are possible, they are preserved until a unique solution is determined. Experimental results show that the depth ambiguity is incrementally reduced if the informative observations are obtained.Keywords3-D reconstructionarticulated objectdepth ambiguityinequality constraints

Benchmark datasets used for testing computer vision (CV) methods often contain little variation in illumination. The methods that perform well on these datasets have been observed to fail under challenging illumination conditions encountered in the real world, in particular, when the dynamic range of a scene is high. The authors present a new dataset for evaluating CV methods in challenging illumination conditions such as low light, high dynamic range, and glare. The main feature of the dataset is that each scene has been captured in all the adversarial illuminations. Moreover, each scene includes an additional reference condition with uniform illumination, which can be used to automatically generate labels for the tested CV methods. We demonstrate the usefulness of the dataset in a preliminary study by evaluating the performance of popular face detection, optical flow, and object detection methods under adversarial illumination conditions. We further assess whether the performance of these applications can be improved if a different transfer function is used.

Traditional supervised learning methods have limitations in labeling speed, scene adaptability and accuracy.Unsupervised learning methods do not require labeling data and can automatically extract the laws, which provides a new idea for image segmentation, especially in medical diagnosis, automatic driving and other highprecision requirements of the scene has an important application value.This study explores unsupervised learningbased image segmentation methods in computer vision, focusing on the improved kernel fuzzy C-mean clustering algorithm (KFCM).The study constructs an image segmentation algorithm with noise robustness by introducing a kernel function instead of Euclidean distance and combining it with super-pixel segmentation technique.The experiments are validated on synthetic, natural and medical images and compared with various classical algorithms.The results show that when 30% Gaussian noise is added to the synthetic image, the segmentation accuracy of the KFCM algorithm reaches 99.8%, which is 12.6% higher than that of the traditional FCM; in the segmentation of the natural image with the addition of mixed noise, the average value of the segmentation coefficient of the KFCM reaches 96.45%, which is 17.47% higher than that of the FCM, and the segmentation entropy is reduced by 34.57%; and in the segmentation of the medical cell image, the KFCM algorithm shows good edge keeping ability in complex noise environment.The study shows that the improved KFCM algorithm significantly improves the image segmentation accuracy and anti-noise performance through the adaptive neighborhood information and kernel mapping, and provides an effective solution for unsupervised image segmentation, which is of practical application value for medical diagnosis, automatic driving and other fields.

There has been much research on computer vision in last three decades. Computer vision methods have been developed for different situations. One example is a detection of human face. For computers face detection is hard. Faces look different from different viewing directions. Facial expressions affect to the look of the face. Each individual person has a unique face. The lightning conditions can vary and so on.However, face detection is currently possible in limited conditions. In addition, there are some methods that can be used for gender recognition [3], face recognition [5] and facial expression recognition [2].Nonetheless, there has been very little research on how to combine these methods. There has also been quite little research on how to apply these methods in human-computer interaction (HCI).Finding sets of techniques that complement each other in a useful way is one research challenge. There are some applications that take advantage of one or two computer vision techniques. For example, Christian and Avery [1] have developed an information kiosk that uses computer vision to detect potential users from a distance. A similar kiosk has been developed by us in the University of Tampere [4]. There are also some games that use simple computer vision techniques for the interaction. However, there are very few applications that use several computer vision techniques together such as face detection, facial expression recognition and gender recognition. Overall, there has been very little effort in combining different techniques.In my research I develop computer vision methods and combine them, so that the combined method can detect face, recognize gender and facial expressions. After successfully combining the methods, it is easier to develop HCI applications that take advantage of computer vision. Applications that can be used by small group of people are my specific interest. These applications allow me to build adaptive user interfaces and analyze the use of computer vision techniques in improving human-computer interaction.