Distant Objects Research Articles

A Stride Toward Wine Yield Estimation from Images: Metrological Validation of Grape Berry Number, Radius, and Volume Estimation

Yield estimation is a key point theme for precision agriculture, especially for small fruits and in-field scenarios. This paper focuses on the metrological validation of a novel deep-learning model that robustly estimates both the number and the radii of grape berries in vineyards using color images, allowing the computation of the visible (and total) volume of grape clusters, which is necessary to reach the ultimate goal of estimating yield production. The proposed algorithm is validated by analyzing its performance on a custom dataset. The number of berries, their mean radius, and the grape cluster volume are converted to millimeters and compared to reference values obtained through manual measurements. The validation experiment also analyzes the uncertainties of the parameters. Results show that the algorithm can reliably estimate the number (MPE=−5%, σ=6%) and the radius of the visible portion of the grape clusters (MPE=0.8%, σ=7%). Instead, the volume estimated in px3 results in a MPE=0.4% with σ=21%, thus the corresponding volume in mm3 is affected by high uncertainty. This analysis highlighted that half of the total uncertainty on the volume is due to the camera–object distance d and parameter R used to take into account the proportion of visible grapes with respect to the total grapes in the grape cluster. This issue is mostly due to the absence of a reliable depth measure between the camera and the grapes, which could be overcome by using depth sensors in combination with color images. Despite being preliminary, the results prove that the model and the metrological analysis are a remarkable advancement toward a reliable approach for directly estimating yield from 2D pictures in the field.

GreenFruitDetector: Lightweight green fruit detector in orchard environment.

Detecting green fruits presents significant challenges due to their close resemblance in color to the leaves in an orchard environment. We designed GreenFruitDetector, a lightweight model based on an improved YOLO v8 architecture, specifically for green fruit detection. In the Backbone network, we replace ordinary convolution with Deformable Convolution to enhance the extraction of geometric features. Additionally, we designed MCAG-DC (Multi-path Coordinate Attention Guided Deformer Convolution) to replace the convolution in C2f, enhancing the Backbone's feature extraction capability when encountering occlusion problems. For the Neck part of the algorithm, we designed a Fusion-neck structure that integrates spatial detail information from feature maps at different scales, thereby enhancing the network's ability to extract multi-scale information. Additionally, we devised a new detection head that incorporates multi-scale information, significantly improving the detection of small and distant objects. Finally, we applied channel pruning techniques to reduce the model size, parameter count, and FLOPs to 50%, 55%, and 44% of the original, respectively. We trained and evaluated the improved model on three green fruit datasets. The accuracy of the improved model reached 94.5%, 84.4%, and 85.9% on the Korla Pear, Guava, and Green Apple datasets, respectively, representing improvements of 1.17%, 1.1%, and 1.77% over the baseline model. The mAP@0.5 increased by 0.72%, 6.5%, and 0.9%, respectively, and the recall rate increased by 1.97%, 1.1%, and 0.49%, respectively.

TouchView: Mid-Air Touch on Zoomable 2D View for Distant Freehand Selection on a Virtual Reality User Interface

Selection is a fundamental interaction element in virtual reality (VR) and 3D user interfaces (UIs). Raycasting, one of the most common object selection techniques, is known to have difficulties in selecting small or distant objects. Meanwhile, recent advancements in computer vision technology have enabled seamless vision-based hand tracking in consumer VR headsets, enhancing accessibility to freehand mid-air interaction and highlighting the need for further research in this area. This study proposes a new technique called TouchView, which utilizes a virtual panel with a modern adaptation of the Through-the-Lens metaphor to improve freehand selection for VR UIs. TouchView enables faster and less demanding target selection by allowing direct touch interaction with the magnified object proxies reflected on the panel view. A repeated-measures ANOVA on the results of a follow-up experiment on multitarget selection with 23 participants showed that TouchView outperformed the current market-dominating freehand raycasting technique, Hybrid Ray, in terms of task performance, perceived workload, and preference. User behavior was also analyzed to understand the underlying reasons for these improvements. The proposed technique can be used in VR UI applications to enhance the selection of distant objects, especially for cases with frequent view shifts.

Designing platforms for digital object-based learning

Over the last decade, object-based learning programs have become a staple of museum collections. These programs encourage and allow patrons to engage with a series of curated objects, offering educational experiences through tactile exploration. Naturally, they are focused on having their audience engage with the physical objects themselves (Chatterjee & Hannan 2016). Applying museological practice and object-based learning in the digital context requires not just presenting digital replica of physical objects, but scaffolding their presentation and platform with purpose, intent, and understanding of the strengths and pitfalls of digital delivery (Beetham & Sharpe 2013; De Kluis, Romp, & Land-Zandstra 2024). As such, digital object-based learning platforms and programs purposefully designed for remote learning and online delivery fill a unique niche in the higher education space and are beginning to come into their own. At Macquarie University, objectbasedlearning.com (an initiative of the Faculty of Arts and stewarded by its Learning Design and Production team) was relaunched in late 2023 following an extensive redesign, with learning designers, academics, and students now working together to provide new remote learning opportunities and experiences for the classroom. This presentation introduces the audience to the refurbished website, explains the ethos behind its redesign with an eye to evolving learning spaces and remote learning, and explores the site’s current and future applications and projects as a case study for designing digital object-based learning. The site was designed with future utility and outreach at its core, offering flexibility in how it presents and categorizes digital objects, and a site layout which reflects the needs of its target audience – schoolteachers. The NSW Stages 5 and 6 Curriculum informs the website’s design, determining how objects are grouped, how users navigate the site, and what information and metadata is prioritized, developed, and displayed. Since its relaunch, the website has been utilized in schools and faculties in NSW to deliver object-based learning experiences and classes. While it is too early to publish on outcomes of the project, early feedback has been positive, and new teaching initiatives have developed around the platform. In 2024, student interns at Macquarie were challenged to develop educational materials, lessons, and workshops which took advantage of the potential of technology-enabled object-based learning. These artefacts were designed to give students a unique object-based learning experience, removing the boundaries of physical distance, financial constraints, and fragility of objects. Moreover, student interns involved in the photogrammetric scanning of objects for the website were themselves enjoying an object-based learning experience, engaging with their materiality and learning how best to present the object in a digital environment.

AI-Based Object Detection, Distance Measurement and Speaking System for Blind Stick

The sense of sight is fundamental to how humans perceive and navigate their surroundings. For visually impaired individuals, this lack of vision creates significant challenges in detecting obstacles and measuring distances, making daily navigation difficult and potentially dangerous. In response to this problem, we propose an AI-based object detection, distance measurement, and speaking system integrated with a blind stick to enhance mobility and independence for the visually impaired. This system leverages cutting-edge artificial intelligence and image processing techniques to provide real-time object detection and distance measurement. By combining ultrasonic sensors with an AI-powered object recognition module, the system accurately identifies obstacles and calculates their distance, offering directional audio feedback to the user. Designed to be compact and user-friendly, the blind stick system provides seamless assistance in both indoor and outdoor environments. The object detection process utilizes advanced algorithms like YOLO (You Only Look Once) to identify obstacles. Distance measurement is performed using ultrasonic sensors to ensure accurate proximity readings. When an obstacle is detected, the system provides immediate auditory feedback, alerting users to the direction and distance of the object. The Google Maps API enhances usability by offering location awareness and route planning, empowering users to navigate with confidence. This AI-based blind stick system aims to improve the mobility and safety of visually impaired individuals, offering a more autonomous experience in their daily lives.

Development Of An Artificial Intelligence Body Gesture Detection Dustbin With An Autonomous System

Effective waste collection is essential in homes and offices to maintain a healthy society, particularly for the elderly and individuals with disabilities. Smart technologies offer an innovative approach to addressing real-world challenges and fostering sustainable development. This system uses a microcontroller, ultrasonic sensors (HC-SR04) to detect the distance or movement of objects, an Arduino Uno as software frame work, a servo motor to open the lid, and a battery for continous power. Automatic activation is triggered by body gestures, making the system both user-friendly and efficient in waste disposal. The ultrasonic sensor detects a user's presence and sends signal to the Arduino Uno board which in turn activates the servo motor to open the dustbin lid. This operation minimizes the risk of contamination, as waste can be disposed without direct contact with the bin. The dustbin is mounted on an autonomous system that moves towards the user and returns to its designated position using features like line-following, path-finding, and Bluetooth-based (HC-05) wireless control for intelligent navigation. Keywords: Ultrasonic sensor, Autonomous system, smart bin, AI, Navigation, Gesture, Body.

Overview of the Fiber System for the Dark Energy Spectroscopic Instrument

The Dark Energy Spectroscopic Instrument (DESI) is a revolutionary instrument designed for precise measurements of cosmic distances and the investigation of dark energy. DESI utilizes 5000 optical fibers to simultaneously measure the spectra of distant objects and aims to measure 40 million galaxies and quasars in a 5 yr survey. One of the critical challenges to DESI’s success was ensuring that the fiber system was not only highly efficient but also delivered a highly stable beam enabling more reliable sky subtraction for measurements of faint objects. We achieved this stability by minimizing the stress on the fiber system during the manufacture and operation of the telescope and fiber positioning robots. We installed the DESI fiber system on the 4 m Mayall telescope with ≥99% of fibers intact, and the instrument has delivered superb optical performance throughout the initial years of the DESI survey, including ≥90% average throughput when injected with a focal ratio of ∼f/3.9 as delivered by the primary focus corrector, excluding fiber absorption losses. The design of DESI required multiple innovations to achieve these requirements, such as cleaved fibers bonded with a UV-curing epoxy to glass ferrules in the focal plane and fusion splicing instead of physical connectors. In this paper, we describe the development, delivery, and installation of the fiber system, the innovations that made the state-of-the-art performance possible, and the key lessons learned that could benefit future projects.

Effects of long-term neural adaptation to habitual sspherical aberration on through-focus visual acuity in adults

We investigated how long-term visual experience with habitual spherical aberration (SA) influences subjective depth of focus (DoF). Nine healthy cycloplegic eyes with habitual SAs of different signs and magnitudes were enrolled. An adaptive optics (AO) visual simulator was used to measure through-focus high-contrast visual acuity after correcting all monochromatic aberrations and imposing + 0.5 μm and − 0.5 μm SAs for a 6-mm pupil. The positive (n = 6) and negative (n = 3) habitual SA groups ranged from 0.17 to 0.8 μm and from − 1.2 to – 0.12 μm for a 6-mm pupil, respectively. Although all optical conditions were identical, and the subjective DoFs were expected to be the same for all participants, the DoFs of individuals differed between the positive and negative habitual SA groups. For the positive habitual SA group, the mean DoF with positive AO-induced SA (2.14 D) was larger than that with negative AO-induced SA (1.88 D); for the negative habitual SA group, a smaller DoF was measured with positive AO-induced SA (1.94 D) than that with negative AO-induced SA (2.14 D). Subjective DoF tended to be larger when the induced SA in terms of sign and magnitude was closer to the participant’s habitual SA. Our findings suggest that neural adaptation to habitual SA compensated for optical blur at multiple object distances, perceptually expanding DoF. As a result, the outcomes of optical treatments for presbyopia may differ due to the neural compensation mechanism influenced by an individual’s visual experience with their habitual optics.

DeployFusion: A Deployable Monocular 3D Object Detection with Multi-Sensor Information Fusion in BEV for Edge Devices.

To address the challenges of suboptimal remote detection and significant computational burden in existing multi-sensor information fusion 3D object detection methods, a novel approach based on Bird's-Eye View (BEV) is proposed. This method utilizes an enhanced lightweight EdgeNeXt feature extraction network, incorporating residual branches to address network degradation caused by the excessive depth of STDA encoding blocks. Meantime, deformable convolution is used to expand the receptive field and reduce computational complexity. The feature fusion module constructs a two-stage fusion network to optimize the fusion and alignment of multi-sensor features. This network aligns image features to supplement environmental information with point cloud features, thereby obtaining the final BEV features. Additionally, a Transformer decoder that emphasizes global spatial cues is employed to process the BEV feature sequence, enabling precise detection of distant small objects. Experimental results demonstrate that this method surpasses the baseline network, with improvements of 4.5% in the NuScenes detection score and 5.5% in average precision for detection objects. Finally, the model is converted and accelerated using TensorRT tools for deployment on mobile devices, achieving an inference time of 138 ms per frame on the Jetson Orin NX embedded platform, thus enabling real-time 3D object detection.

A Star‐Nose‐Inspired Bionic Soft Robot for Nonvisual Spatial Detection and Reconstruction

The star‐nosed mole is recognized as a tactilely sensitive mammal due to its unique nose, which facilitates spatial detection in dark environments through touch using its appendages enveloped in numerous sensory receptors. This article introduces a bionic soft robot inspired by the star‐nosed mole, which combines a pneumatic soft platform with a polydimethylsiloxane–polyethylene terephthalate cylindrical tactile sensor array based on bilayer single‐electrode triboelectric nanogenerators, mimicking the muscle tissue of the mole's nose and the cylindrical appendages surrounded by Eimer's organs. The cylindrical sensor array enables multiangle spatial detection without an external power supply and remains unaffected by external materials. By implementing a constant curvature model for robot motion control, positional information is provided for the contact points between the cylindrical sensor array and the external environment. The robot effectively discriminates the distance and shape of various objects and achieves nonvisual 3D spatial detection and reconstruction in real‐world scenarios. This work presents a novel bionic approach for 3D spatial detection in nonvisual environments.

Research on efficient matching method of coal gangue recognition image and sorting image

When the coal gangue sorting robot sorts coal gangue, the position of the target coal gangue will change due to belt slippage, deviation, and speed fluctuations of the belt conveyor. This will cause the robotic to fail in grasping or miss grasping. We have developed a solution to this problem: the IMSSP-Net two-stage network gangue image fast matching method. This method will reacquire the target gangue position information and improve the robot’s grasping precision and efficiency. In the first stage, we use SuperPoint to guarantee the scene adaptability and credibility of feature point extraction. We have enhanced Superpoint’s ability to detect feature points further by using the improved Multi-scale Retinex with Color Restoration enhancement algorithm. In the second stage, we introduce SuperGlue for feature matching to improve the robustness of the matching network. We eliminated erroneous feature matching point pairs and improved the accuracy of image matching by adopting the PROSAC algorithm. We conducted image matching comparison experiments under different object distances, scales, rotation angles, and complex conditions. The experimental platform adopts the double-manipulator truss-type coal gangue sorting robot independently developed by the team. The matching precision, recall, and matching time of the method are 98.2%, 98.3%, and 84.6ms, respectively. The method can meet the requirements of efficient and accurate matching between coal gangue recognition images and sorting images.

Physical properties of trans-Neptunian object (143707) 2003 UY117 derived from stellar occultation and photometric observations

Context. Trans-Neptunian objects (TNOs) are considered to be among the most primitive objects in our Solar System. Knowledge of their primary physical properties is essential for understanding their origin and the evolution of the outer Solar System. In this context, stellar occultations are a powerful and sensitive technique for studying these distant and faint objects. Aims. We aim to obtain the size, shape, absolute magnitude, and geometric albedo for TNO (143707) 2003 UY117. Methods. We predicted a stellar occultation by this TNO for 2020 October 23 UT and ran a specific campaign to investigate this event. We derived the projected profile shape and size from the occultation observations by means of an elliptical fit to the occultation chords. We also performed photometric observations of (143707) 2003 UY117 to obtain the absolute magnitude and the rotational period from the observed rotational light curve. Finally, we combined these results to derive the three-dimensional shape, volume-equivalent diameter, and geometric albedo for this TNO. Results. From the stellar occultation, we obtained a projected ellipse with axes of (282 ± 18) × (184 ± 32) km. The area-equivalent diameter for this ellipse is Deq,A = 228 ± 21 km. From our photometric R band observations, we derived an absolute magnitude of HV = 5.97 ± 0.07 mag using V − R = 0.46 ± 0.07 mag, which was derived from a V band subset of these data. The rotational light curve has a peak-to-valley amplitude of ∆m = 0.36 ± 0.13 mag. We find the most likely rotation period to be P = 12.376 ± 0.0033 hours. By combining the occultation with the rotational light curve results and assuming a triaxial ellipsoid, we derived axes of a × b × c = (332 ± 24) km × (216 ± 24) km × (180−24+28) km for this ellipsoid, and therefore a volume-equivalent diameter of Deq,V = 235 ± 25 km. Finally, the values for the absolute magnitude and for the area-equivalent diameter yield a geometric albedo of pV = 0.139 ± 0.027.

A JWST Pure-Parallel Search for the First Galaxies With PANORAMIC

The James Webb Space Telescope offers unparalleled capabilities for observing the most distant objects in the universe, allowing us to study the first galaxies to form. In this work, the Lyman-break technique and spectral energy distribution fitting were used to analyse the JWST PANORAMIC survey and identify 26 robust galaxy candidates at redshifts greater than 9.5, including three around redshift 14.5. These candidates will make excellent targets for follow-up spectroscopy. The derived UV luminosity function at z = 14.5 is consistent with literature determinations at similar redshifts and implies a modest evolution in the number density of galaxies from z ∼ 14 to z ∼ 11. Future research based on this work could determine when the first galaxies formed, confirming or challenging current theories of cosmic evolution.

Dexterous Manipulation Based on Object Recognition and Accurate Pose Estimation Using RGB-D Data.

This study presents an integrated system for object recognition, six-degrees-of-freedom pose estimation, and dexterous manipulation using a JACO robotic arm with an Intel RealSense D435 camera. This system is designed to automate the manipulation of industrial valves by capturing point clouds (PCs) from multiple perspectives to improve the accuracy of pose estimation. The object recognition module includes scene segmentation, geometric primitives recognition, model recognition, and a color-based clustering and integration approach enhanced by a dynamic cluster merging algorithm. Pose estimation is achieved using the random sample consensus algorithm, which predicts position and orientation. The system was tested within a 60° field of view, which extended in all directions in front of the object. The experimental results show that the system performs reliably within acceptable error thresholds for both position and orientation when the objects are within a ±15° range of the camera's direct view. However, errors increased with more extreme object orientations and distances, particularly when estimating the orientation of ball valves. A zone-based dexterous manipulation strategy was developed to overcome these challenges, where the system adjusts the camera position for optimal conditions. This approach mitigates larger errors in difficult scenarios, enhancing overall system reliability. The key contributions of this research include a novel method for improving object recognition and pose estimation, a technique for increasing the accuracy of pose estimation, and the development of a robot motion model for dexterous manipulation in industrial settings.

An end-to-end model of active electrosensation.

1Weakly electric fish localize and identify objects by sensing distortions in a self-generated electric field. Fish can determine the resistance and capacitance of an object, for example, even though the field distortions being sensed are small and highly-dependent on object distance and size. Here we construct a model of the responses of the fish's electroreceptors on the basis of experimental data, and we develop a model of the electric fields generated by the fish and the distortions due to objects of different resistances and capacitances. This provides us with an accurate and efficient method for generating large artificial data sets simulating fish interacting with a wide variety of objects. Using these sets, we train an artificial neural network (ANN), representing brain areas downstream of electroreceptors, to extract the 3D location, size, and electrical properties of objects. The model performs best if the ANN operates in two stages: first estimating object distance and size and then using this information to extract electrical properties. This suggests a specific form of modularity in the electrosensory system that can be tested experimentally and highlights the potential of end-to-end modeling for studies of sensory processing.

3D alignment of distant patterns with deep-subwavelength precision using metasurfaces

Measurement of the relative positions of two objects in three dimensions with sub-nanometer precision is essential to fundamental physics experiments and applications such as aligning multi-layer patterns of semiconductor chips. Existing methods, which rely on microscopic imaging and registration of distant patterns, lack the required accuracy and precision for the next generation of three-dimensional (3D) chips. Here we show that 3D misalignment between two distant objects can be measured using metasurface alignment marks, a laser, and a camera with sub-nanometer precision. Through simulations, we demonstrate that the shot noise-limited precisions of the lateral and axial misalignments between the marks are λ0/50, 000 and λ0/6, 300 (λ0: laser’s wavelength), respectively. With its high precision and simplicity, the technique enables the next generation of 3D-integrated optical and electronic chips and paves the way for developing cost-effective and compact sensors relying on sub-nanometer displacement measurements.

Analysis of alternatives to the accelerating expansion of the Universe

Observations from the James Webb Space Telescope (JWST) in recent years pose serious challenges to standard cosmology. Such a situation prompts to reconsider the models presented as alternatives to the Lambda-Cold Dark Matter (ΛCDM) model. In this work, a number of such models are considered, including models related to modifying gravity, models related to intrinsic luminosity of supernovae type Ia (SNe Ia), and models related to red shift. The accelerated expansion of the Universe is associated with the red shift of distant objects, and standard cosmology assumes that this red shift is caused by cosmological expansion. In this paper, we consider the alternative possibility that the red shift of distant objects may also be due to the phenomenon of red shift of light in the intergalactic and interstellar media.

Path Tracing-Inspired Modeling of Non-Line-of-Sight SPAD Data.

Non-Line of Sight (NLOS) imaging has gained attention for its ability to detect and reconstruct objects beyond the direct line of sight, using scattered light, with applications in surveillance and autonomous navigation. This paper presents a versatile framework for modeling the temporal distribution of photon detections in direct Time of Flight (dToF) Lidar NLOS systems. Our approach accurately accounts for key factors such as material reflectivity, object distance, and occlusion by utilizing a proof-of-principle simulation realized with the Unreal Engine. By generating likelihood distributions for photon detections over time, we propose a mechanism for the simulation of NLOS imaging data, facilitating the optimization of NLOS systems and the development of novel reconstruction algorithms. The framework allows for the analysis of individual components of photon return distributions, yielding results consistent with prior experimental data and providing insights into the effects of extended surfaces and multi-path scattering. We introduce an optimized secondary scattering approach that captures critical multi-path information with reduced computational cost. This work provides a robust tool for the design and improvement of dToF SPAD Lidar-based NLOS imaging systems.

Improved yolov5 algorithm combined with depth camera and embedded system for blind indoor visual assistance

To assist the visually impaired in their daily lives and solve the problems associated with poor portability, high hardware costs, and environmental susceptibility of indoor object-finding aids for the visually impaired, an improved YOLOv5 algorithm was proposed. It was combined with a RealSense D435i depth camera and a voice system to realise an indoor object-finding device for the visually impaired using a Raspberry Pi 4 B device as its core. The algorithm uses GhostNet instead of the YOLOv5s backbone network to reduce the number of parameters and computation of the model, incorporates an attention mechanism (coordinate attention), and replaces the YOLOv5 neck network with a bidirectional feature pyramid network to enhance feature extraction. Compared to the YOLOv5 model, the model size was reduced by 42.4%, number of parameters was reduced by 47.9%, and recall rate increased by 1.2% with the same precision. This study applied the improved YOLOv5 algorithm to an indoor object-finding device for the visually impaired, where the searched object was input by voice, and the RealSense D435i was used to acquire RGB and depth images to realize the detection and ranging of the object, broadcast the specific distance of the target object by voice, and assist the visually impaired in finding the object.

ETFE: Efficient transformer with feature enhancement for semantic segmentation

Abstract Despite the powerful capabilities of Transformers in relation to modeling, their effectiveness in capturing multi-scale object features in image-based tasks is often limited. This limitation arises from the diverse shapes and distances between objects in natural scenes, which pose challenges for Transformers to accurately capture object sizes and distances. To overcome this problem, we propose an effective Transformer which extracts multi-scale features at different resolutions. First, we leverage a multi-head attention mechanism to extract richer semantic features at various resolutions. The semantic features are then passed through the Feature Gate to aggregate multi-scale semantic features. Finally, Attentional Feature Enhancement further strengthens the semantic information of target features, enabling the modeling of dependencies among multi-scale features. Comprehensive experiments conducted on the Cityscapes and ADE20K datasets have shown that our model outperforms competing methods in both performance and accuracy.