Shape Signature Research Articles

Use of 3D chaos game representation to quantify DNA sequence similarity with applications for hierarchical clustering

A 3D chaos game is shown to be a useful way for encoding DNA sequences. Since matching subsequences in DNA converge in space in 3D chaos game encoding, a DNA sequence’s 3D chaos game representation can be used to compare DNA sequences without prior alignment and without truncating or padding any of the sequences. Two proposed methods inspired by shape-similarity comparison techniques show that this form of encoding can perform as well as alignment-based techniques for building phylogenetic trees. The first method uses the volume overlap of intersecting spheres and the second uses shape signatures by summarizing the coordinates, oriented angles, and oriented distances of the 3D chaos game trajectory. The methods are tested using: (1) the first exon of the beta-globin gene for 11 species, (2) mitochondrial DNA from four groups of primates, and (3) a set of synthetic DNA sequences. Simulations show that the proposed methods produce distances that reflect the number of mutation events; additionally, on average, distances resulting from deletion mutations are comparable to those produced by substitution mutations.

Satellite Imagery Analysis and Plane Detection

Monitoring natural vegetation and detecting planes in satellite imagery are critical tasks in remote sensing, with applications ranging from environmental conservation to security and surveillance. This project aims to develop an effective method for analyzing natural vegetation and detecting planes by utilizing satellite imagery and applying advanced image processing and machine learning techniques. By leveraging various features such as vegetation indices, texture, shape, and spectral signatures, we aim to build predictive models that accurately classify vegetation types and identify planes. This paper discusses the methodology, including data collection, preprocessing, feature extraction, model training, and evaluation, ultimately highlighting the models' performance and potential applications in real-world scenarios. Keywords— Vegetation Analysis,Deep learning ,Plane Detection.

Research on visualization of cotton canopy structure and extraction of feature parameters based on dual-perspective point cloud data

ABSTRACT Cotton is one of the crops that requires the most time and labor. Precision agriculture technology is required for efficient management of cotton, and the identification of cotton attribute information in the field is a necessary and crucial step towards implementing precision agriculture. Unmanned aerial vehicles (UAVs) and Light Detection and Ranging (LiDAR) have evolved into essential instruments for plant phenotyping research. In this study, in order to address the demand for cotton attribute identification over wide areas in the field, an airborne LiDAR system was built based on LiDAR detection technology. This work acquired a dual-view point cloud of a cotton field in order to address the high density and low accuracy of the cotton point cloud attributes. Following pre-processing of the data, the point cloud was first coarsely regenerated using a combination of Fast Point Feature Histograms (FPFH) and Intrinsic Shape Signatures (ISS) techniques. The dual-view point cloud registration was then refined and finished using an Iterative Closest Point (ICP) algorithm. The height of the cotton plant was determined using the reconstructed point cloud of the cotton canopy, and a method combining Graham’s algorithm and the Alpha-Shape algorithm was suggested to determine the porosity of the cotton layers. The findings revealed that the root mean square errors (RMSE) between calculated and measured values of cotton plant height and stratified porosity were, respectively, 3.98 cm and 5.21%, and that their mean absolute percentage errors (MAPE) were 4.39% and 9.31%, with correlation coefficients ( R 2 ) of 0.951 and 0.762, respectively. On the whole, our study has demonstrated the effectiveness of the proposed method in terms of providing accurate and reliable cotton parameters in agriculture.

A comparative study of principal component analysis and kernel principal component analysis for photogrammetric shape-based turbine blade damage analysis

Photogrammetry is popular as a non-contact full-field data acquisition technique for machine condition monitoring purposes. Two popular implementations thereof are Digital Image Correlation (DIC) and 3D Point Tracking (3DPT). Since these two approaches require surface preparation in the form of applying speckle patterns or discrete markers, their use is negated in several industrial applications, such as the online condition monitoring and/or assessment of horizontal axis wind turbines. A shape-based photogrammetric approach that focuses on analysing changes in the form of a rotating blade’s boundary contour is a viable alternative that does not require any surface preparation. 3D shapes of a blade at a particular instance can be extracted from a pair of stereoscopic images of the blade. Shape Principal Component Descriptors (SPCDs) determined from applying Principal Component Analysis (PCA) to Fourier coefficients of chain-code shape signatures of the blade contour can be determined. These can be regarded as indicators of the form of the shape, and as the blade rotates, variations in the SPCDs can be investigated to better understand the dynamics of the blades. This paper focuses on the application and performance evaluation of data reduction and classification techniques for a novel shape-based photogrammetry condition monitoring technique. Investigations are conducted to show that applying data reduction methods to raw time domain SPCDs can result in successful classification of differently damaged blades. Post-processing strategies are developed to ensure a more robust shape based condition monitoring tool for analysing turbine blades. Kernel Principal Component Analysis (KPCA) is implemented and it is shown that it out-performs the conventional PCA in terms of classifying different blade damage modes. The feasibility of using multi-domain statistical features as feature vectors to which PCA or KPCA is applied for classification purposes is also investigated. Results indicating how well differently damaged blades can be distinguished are provided, and it is clearly illustrated that multi-domain statistical features are more robust to noise contamination in the signals compared to using the raw SPCDs data.

A Mars Local Terrain Matching Method Based on 3D Point Clouds

To address the matching challenge between the High Resolution Imaging Science Experiment (HiRISE) Digital Elevation Model (DEM) and the Mars Orbiter Laser Altimeter (MOLA) DEM, we propose a terrain matching framework based on the combination of point cloud coarse alignment and fine alignment methods. Firstly, we achieved global coarse localization of the HiRISE DEM through nearest neighbor matching of key Intrinsic Shape Signatures (ISS) points in the Fast Point Feature Histograms (FPFH) feature space. We introduced a graph matching strategy to mitigate gross errors in feature matching, employing a numerical method of non-cooperative game theory to solve the extremal optimization problem under Karush–Kuhn–Tucker (KKT) conditions. Secondly, to handle the substantial resolution disparities between the MOLA DEM and HiRISE DEM, we devised a smoothing weighting method tailored to enhance the Voxelized Generalized Iterative Closest Point (VGICP) approach for fine terrain registration. This involves leveraging the Euclidean distance between distributions to effectively weight loss and covariance, thereby reducing the results’ sensitivity to voxel radius selection. Our experiments show that the proposed algorithm improves the accuracy of terrain registration on the proposed Curiosity landing area’s, Mawrth Vallis, data by nearly 20%, with faster convergence and better algorithm robustness.

Generative vs. Non-Generative Models in Engineering Shape Optimization

Generative models offer design diversity but tend to be computationally expensive, while non-generative models are computationally cost-effective but produce less diverse and often invalid designs. However, the limitations of non-generative models can be overcome with the introduction of augmented shape signature vectors (SSVs) to represent both geometric and physical information. This recent advancement has inspired a systematic comparison of the effectiveness and efficiency of generative and non-generative models in constructing design spaces for novel and efficient design exploration and shape optimization, which is demonstrated in this work. These models are showcased in airfoil/hydrofoil design, and a comparison of the resulting design spaces is conducted in this work. A conventional generative adversarial network (GAN) and a state-of-the-art generative model, the performance-augmented diverse generative adversarial network (PaDGAN), are juxtaposed with a linear non-generative model based on the coupling of the Karhunen–Loève Expansion and a physics-informed shape signature vector (SSV-KLE). The comparison demonstrates that, with an appropriate shape encoding and a physics-augmented design space, non-generative models have the potential to cost-effectively generate high-performing valid designs with enhanced coverage of the design space. In this work, both approaches were applied to two large foil profile datasets comprising real-world and artificial designs generated through either a profile-generating parametric model or a deep-learning approach. These datasets were further enriched with integral properties of their members’ shapes, as well as physics-informed parameters. The obtained results illustrate that the design spaces constructed by the non-generative model outperform the generative model in terms of design validity, generating robust latent spaces with no or significantly fewer invalid designs when compared to generative models. The performance and diversity of the generated designs were compared to provide further insights about the quality of the resulting spaces. These findings can aid the engineering design community in making informed decisions when constructing design spaces for shape optimization, as it has been demonstrated that, under certain conditions, computationally inexpensive approaches can closely match or even outperform state-of-the art generative models.

Dynamic Path Planning Based on 3D Cloud Recognition for an Assistive Bathing Robot

Assistive bathing robots have become a popular point due to their metrics, such as a humanoid working approach in the solution of elder care. However, the abilities of dynamic recognition and path planning are the key to obtain the advantages. This paper proposes a novel approach to recognize and track the dynamical human back, and path planning on it via a 3D point cloud. Firstly, the human back geometric features are recognized through coarse-to-fine alignment. The Intrinsic Shape Signature (ISS) algorithm combined with the Fast Point Feature Histogram (FPFH) and the Sample Consensus Initial Alignment (SAC-IA) algorithm are adopted to complete the coarse alignment, and the Iterative Closest Point (ICP) algorithm is applied to the fine alignment to improve the accuracy of recognition. Then, the dynamic transformation matrix between the contiguous recognized back is deduced based on spatial motion between two adjacent recognized back point clouds. The path can be planned on the tracked human back. Finally, a set of testing experiments are conducted to verify the proposed algorithm. The results show that the running time is reduced by 66.18% and 96.29% compared with the other two common algorithms, respectively.

Sonic boom propagation in urban canyons using a combined ray tracing/radiosity method.

Sonic boom propagation over land is being studied to ensure a minimal impact on the population in the event that supersonic flight over land becomes permissible. Sonic boom behavior in and around urban areas is particularly important due to the high density of people residing in cities and the increased probability of impacting large numbers of people if urban areas lie in the flight path. This study models sonic booms around urban canyons using a combined ray tracing/radiosity method. The impacts of several parameters, such as diffusion, arrival angle, building heights, and canyon width, on the sound field were explored. The results showed that without diffusion, there was no real trend as the canyon height and width and arrival angles were varied. There were strong shadow zones where no sound was detected as this model does not include diffraction. In other locations, between one and four boom events were received. The resulting perceived level in dB (PLdB) varied from 0 in the shadow zones to 94 dB. Diffuse reflections was the parameter that had the greatest impact on the resulting signatures. Parameters that caused an increased number of reflections showed significant changes in the signature shape and a dramatic reduction in the PLdB.

Incorporating Sequence-Dependent DNA Shape and Dynamics into Transcriptome Data Analysis.

Differentially expressed genes in a cellular context may be co-regulated by the same transcription factor. However, in the absence of a concurrent transcription factor binding data, such interactions are difficult to detect, especially at the single cell expression level. Motif enrichments in such genes can be used to gain insight into differential expressions caused by the shared upstream TFs. However, it is now established that many genes are co-regulated by the same TF due to a shared DNA shape or sequence-dependent conformational dynamics instead of sequence motif. In this work, we demonstrate how, starting from a gene expression data, such DNA shape and dynamics signatures can be potentially detected using publicly available tools, including DynaSeq, developed in our group for predicting the sequence-dependent components of these DNA shapefeatures.

Identification of Aedes aegypti and Aedes albopictus eggs based on image processing and elliptic fourier analysis

Dengue hemorrhagic fever is a worldwide epidemic caused by dengue virus and spread by infected female mosquitoes. The two main mosquito species vectors of the dengue virus are Aedes aegypti and Aedes albopictus. Conventionally, the identification of these two species’ egg is time-consuming which makes vector control more difficult. However, although attempts on efficiency improvements by providing automatic identification have been conducted, the earliest stage is at the larval stage. In addition, there are currently no studies on classifying to distinguish the two vectors during the egg stage based on their digital image. A total of 140 egg images of Aedes aegypti and Aedes albopictus were collected and validated by rearing them individually to become adult mosquitoes. Image processing and elliptic Fourier analysis were carried out to extract and describe the shape difference of the two vectors’ eggs. Machine learning algorithms were then used to classify the shape signatures. Morphometrically, the two species’ eggs were significantly different, which Aedes albopictus were smaller in size. Egg-shape contour reconstructions of principal components and Multivariate Analysis of Variance (MANOVA) revealed that there is a significant difference (p value < 0.000) in shape between two species’ eggs at the posterior end. Based on Wilk’s lambda of the MANOVA results, the classification could be done using only the first 3 principal components. Classification of the test data yielded an accuracy of 85.00% and F1 score 84.21% with Linear Discriminant Analysis applying default hyperparameter. Alternatively, k-Nearest Neighbors with optimal hyperparameter yielded a higher classification result with 87.50% and 87.18% of accuracy and F1 score, respectively. These results demonstrate that the proposed method can be used to classify Aedes aegypti and Aedes albopictus eggs based on their digital image. This method provides a foundation for improving the identification and surveillance of the two vectors and decision making in developing vector control strategies.

A method for detecting tomato canopies’ phenotypic traits based on improved skeleton extraction algorithm

Automatic acquisition of tomato canopies’ phenotypic traits is essential for tomato varieties’ selection and scientific cultivation. Due to the infinite growth characteristics of tomato, its organ development is stochastic and the canopies' internal structure of is also complex. These make it challenging to obtain organs’ detailed phenotypic traits. Thus, this work proposed a method for detecting tomato canopies’ phenotypic traits based on improved skeleton extraction algorithm (ISEA). Firstly, after collecting tomato canopies' point cloud data from multiple perspectives, this work reconstructed its three-dimensional (3D) model accurately. Secondly, the least squares method was used to simplify the spatial contraction model of the Laplace Skeleton Extraction algorithm to obtain the tomatoes’ skeleton point set. On this basic, Greedy algorithm was used to optimise the Edge Collapse algorithm to extract more accurate and reliable skeleton structure. Then, in conjunction with the canopy growth characteristics of the crop and the Intrinsic Shape Signatures (ISS) principle, the simplified skeleton structure was subjected to local principal component analysis (PCA), which achieved the separation of tomatoes’ main stem and leaves. Finally, a modelling algorithm based on Delaunay triangulation was applied to construct the separated organs’ model to calculate phenotypic traits such as stem diameter, leaf area index and average leaf inclination. The calculated results were also compared with the measured values at different growth stages for performance evaluation. The average precision, average recall, average accuracy and micro F1 score of ISEA were 0.9144, 0.7751, 0.7243 and 0.8306, respectively. The overall R2 between calculated values and measured values for stem diameter, leaf area index and average leaf inclination were 0.9638, 0.9067, and 0.9428, and the root mean square errors (RMSE) were 0.3922, 0.0029, and 0.0186, respectively. As a result, the proposed method can extract a simple skeleton from the complex tomato canopy and calculate phenotypic traits accurately. It also provided solid technical support for studying the interaction about “genotype-phenotype-envirotype” in tomato.

A Fast Registration Method for MEMS LiDAR Point Cloud Based on Self-Adaptive Segmentation

The Micro-Electro-Mechanical System (MEMS) LiDAR point cloud in autonomous vehicles has a large deflection range, which results in slow registration speed and poor applicability. To maximize speed, an improved Normal Distribution Transform (NDT) method that integrates point cloud density features has been proposed. First, the point cloud is reduced using a modified voxel filter and a pass-through filter. Next, the Intrinsic Shape Signature (ISS) algorithm is utilized to analyze the point cloud features and extract key points; the Four-Point Congruent Set (4PCS) algorithm is then employed to calculate the initial pose under the constraints of the key point set to complete the coarse registration. Finally, the self-adaptive segmentation model is constructed by using a K-D tree to obtain the density features of key points, and the NDT algorithm is combined with this model to form an SSM-NDT algorithm, which is used for fine registration. Each algorithm was compared on the autonomous vehicle dataset PandaSet and actual collected datasets. The results show that the novel method increases the speed by at least 60% and takes into account good registration accuracy and strong anti-interference.

Lithofacies, Depofacies and Reservoir Characteristics of Well TMG-08, Opolo Field, Niger Delta

Sediments within the depth intervals of 2834-6620.9 ft in Well TMG-08 of Opolo Field, Niger Delta, were investigated with the aim of establishing its lithofacies, depositional environments and petrophysical characteristics using a suite of Well-Logs. The Shale lithology is more dominant and of thicker units than the sand at the upper section of the log which could be interpreted as sediments of the Akata Formation. Five sand bodies were identified within the study interval. The shapes of the gamma ray signatures were funnel, cylindrical and symmetrical. Prograding, aggradational and combined prograding and retrograding parasequences were identified from the stacking patterns of the gamma ray curves. The environments of deposition delineated were Transgressive shelf sands and mixed Tidal flat environment, Crevasse splay, River mouth bar, Delta front shoreface, and Fluvial channels, Tidal sands, Prograding delta distributaries. The predicted porosity and permeability show moderate to good quality reservoirs. The average porosity value (0.13 *100= 13% Ranging from Poor to moderate), with a moderate permeability Value (16.87mD) due to the presence of high volume of shale in the reservoirs. The thicknesses of the reservoir are small averaging 5.5ft (16.92m). The depositional environment shows that sand B and C are continuous within the reservoir. The environment of deposition of the study area lies within the marginal marine

A Stereo-Vision-Based Spatial-Positioning and Postural-Estimation Method for Miniature Circuit Breaker Components

This paper proposes a stereo-vision-based method that detects and registers the positions and postures of muti-type, randomly placed miniature circuit breaker (MCB) components within scene point clouds acquired by a 3D stereo camera. The method is designed to be utilized in the flexible assembly of MCBs to improve the precision of gripping small-sized and complex-structured components. The proposed method contains the following stages: First, the 3D computer-aided design (CAD) models of the components are converted to surface point cloud models by voxel down-sampling to form matching templates. Second, the scene point cloud is filtered, clustered, and segmented to obtain candidate-matching regions. Third, point cloud features are extracted by Intrinsic Shape Signatures (ISSs) from the templates and the candidate-matching regions and described by Fast Point Feature Histogram (FPFH). We apply Sample Consensus Initial Alignment (SAC-IA) to the extracted features to obtain a rough matching. Fourth, fine registration is performed by employing Iterative Closest Points (ICPs) with a K-dimensional Tree (KD-tree) between the templates and the roughly matched targets. Meanwhile, Random Sample Consensus (RANSAC), which effectively solves the local optimal problem in the classic ICP algorithm, is employed to remove the incorrectly matching point pairs for further precision improvement. The experimental results show that the proposed method achieves spatial positioning errors smaller than 0.2 mm and postural estimation errors smaller than 0.5°. The precision and efficiency meet the requirements of the robotic flexible assembly for MCBs.

Morphological and dietary adaptations to different socio-economic systems in Chalcolithic dogs

Dogs have cohabited with humans since the Upper Paleolithic and their lifestyle and diet during late prehistory probably already depended on the role they played in past societies. Here, we used a combination of stable isotope analyses and three-dimensional geometric morphometrics to test for differences in, and associations between, diet and mandibular morphology based on 150 dogs of three sites of the Chalcolithic Gumelniţa culture in Romania (4550–3900 cal. BCE) characterized by different socio-economic systems. At Hârşova-tell and Borduşani-Popină, where the subsistence economy is mainly based on herding, dogs have a variable diet that is rich in domestic animals (sheep, cattle, pig) and may contain fish. In contrast, at Vităneşti-Măgurice, where hunting predominates, the diet of dogs is more specialized towards large game (red deer, aurochs, wild horse), reflecting the composition of human food refuse. Moreover, dogs have more robust (but not larger) mandibles at this site with shapes suggesting a greater importance of the temporal muscle important for the capture of large prey and the breaking of large bones. The strong covariation between mandible shape and stable isotope signatures suggests functional adaptations to diet. Overall, our results support the idea that prehistoric dogs adapted to human lifestyles.

Otolith shape and elemental signatures provide insights into the connectivity of euryhaline Chelon labrosus inhabiting two close estuaries with different burdens of xenoestrogens in the Southern Bay of Biscay

Intersex gonads have been observed in thicklip grey mullet Chelon labrosus, inhabiting estuaries with high burdens of xenoestrogens in the Southeast Bay of Biscay, but knowledge of population connectivity among estuaries is lacking for this euryhaline fish species. This study investigates the population structure of C. labrosus using otolith shape and elemental signatures of 60 adults (overall length ∼ 38 cm) from two estuaries 21 nautic miles apart, one with a high incidence of intersex condition (Gernika), and the other one pristine (Plentzia). Otolith shape analyses were performed using elliptical Fourier descriptors, while elemental signatures of whole sagittae were obtained by inductively coupled plasma mass spectrophotometry. Univariate and multivariate statistics were applied to determine if otolith signatures show patterns of homogeneity between estuaries. The data indicated significant differences in the otolith shape and elemental composition between mullets of Gernika and Plentzia. Elemental differences were mainly driven by Sr, Li (both higher in Plentzia) and Ba (higher in Gernika). The 98% re-classification success rate obtained from stepwise linear discriminant function analysis suggests that Gernika and Plentzia individuals form separated population units. The limited connectivity between these two close estuaries would indicate a different life history of exposure to chemicals, which might explain the high prevalence of intersex condition in Gernika and its absence in Plenztia.

Robust features extraction from shape signature for fish images classification

Recently, the process of fish species classification has become one of the most challenging problems addressed by researchers. In this work, a robust scheme to classify fish images based on robust feature extraction from shape signatures is proposed. First, the image contour is fitted using one of the common approaches named radial basis function neural network (RBFNN) fitting to obtain image centroid. Afterward, prominent features from the shape signature are extracted. These features are representative of fish shapes because they can distinguish the characteristics of each class as well as being relatively robust to scale and rotation changes. Finally, for the classification process purpose, RBFNN is used again for image classification against one of the most commonly used classification techniques called support vector machine (SVM). The proposed paradigm has been applied to a standard fish dataset acquired from a live video dataset grouped into twenty-three clusters representing specific fish species. The resulting accuracy based on SVM and RBFNN was 90.41% and 98.04%, respectively.

POINT CLOUD REGISTRATION USING LASER DATA FROM AN ORANGE ORCHARD

Abstract. Mobile laser systems have been used for close-range applications, such as agricultural management, due to the high penetrability of the laser beam enabling a unique 3D representation of the plant structure. However, some challenges remain in generating 3D mapping in agricultural environments. For instance, orange orchards are composed of trees with dense canopies which the laser scanner cannot penetrate for stem mapping. Therefore, most of the laser point clouds are pulses reflected from leaves and ground. This paper analyses approaches to detect keypoints, extract features and register the point clouds acquired with a laser scanner in an orange orchard. Three keypoints extraction methods (Uniform Sampling – US, 3D Harris and 3D Intrinsic Shape Signatures – 3D ISS), SHOT feature extraction and global registration methods (ICP and CPD) were evaluated. The results showed that improvements are still necessary for point cloud registration for orange orchards. In feature-based matching methods, an approach to filter the mismatches is needed to improve the estimation of the translation and rotation parameters. In the global registration methods, initial values of the trajectory are needed for ICP. CPD achieved good results for five sequence scans without initial values.

A novel Chr1-miR-200 driven whole transcriptome signature shapes tumor immune microenvironment and predicts relapse in early-stage lung adenocarcinoma

BackgroundIn Lung adenocarcinoma (LUAD), targeted therapies and immunotherapies have moved from metastatic to early stage and stratification of the relapse risk becomes mandatory. Here we identified a miR-200 based RNA signature that delineates Epithelial-to-mesenchymal transition (EMT) heterogeneity and predicts survival beyond current classification systems.MethodsA miR-200 signature was identified using RNA sequencing. We scored the miR-200 signature by WISP (Weighted In Silico Pathology), used GSEA to identify pathway enrichments and MCP-counter to characterize immune cell infiltrates. We evaluate the clinical value of this signature in our series of LUAD and using TCGA and 7 published datasets.ResultsWe identified 3 clusters based on supervised classification: I is miR-200-sign-down and enriched in TP53 mutations IIA and IIB are miR-200-sign-up: IIA is enriched in EGFR (p < 0.001), IIB is enriched in KRAS mutation (p < 0.001). WISP stratified patients into miR-200-sign-down (n = 65) and miR-200-sign-up (n = 42). Several biological processes were enriched in MiR-200-sign-down tumors, focal adhesion, actin cytoskeleton, cytokine/receptor interaction, TP53 signaling and cell cycle pathways. Fibroblast, immune cell infiltration and PDL1 expression were also significantly higher suggesting immune exhaustion. This signature stratified patients into high-vs low-risk groups, miR-200-sign-up had higher DFS, median not reached at 60 vs 41 months and within subpopulations with stage I, IA, IB, or II. Results were validated on TCGA data on 7 public datasets.ConclusionThis EMT and miR-200-related prognostic signature refines prognosis evaluation independently of tumor stage and paves the way towards assessing the predictive value of this LUAD clustering to optimize perioperative treatment.

A Method for Predicting Canopy Light Distribution in Cherry Trees Based on Fused Point Cloud Data

A proper canopy light distribution in fruit trees can improve photosynthetic efficiency, which is important for improving fruit yield and quality. Traditional methods of measuring light intensity in the canopy of fruit trees are time consuming, labor intensive and error prone. Therefore, a method for predicting canopy light distribution in cherry trees was proposed based on a three-dimensional (3D) cherry tree canopy point cloud model fused by multiple sources. First, to quickly and accurately reconstruct the 3D cherry tree point cloud model, we propose a global cherry tree alignment method based on a binocular depth camera vision system. For the point cloud data acquired by the two cameras, a RANSAC-based orb calibration method is used to externally calibrate the cameras, and the point cloud is coarsely aligned using the pose transformation matrix between the cameras. For the point cloud data collected at different stations, a coarse point cloud alignment method based on intrinsic shape signature (ISS) key points is proposed. In addition, an improved iterative closest point (ICP) algorithm based on bidirectional KD-tree is proposed to precisely align the coarse-aligned cherry tree point cloud data to achieve point cloud data fusion and obtain a complete 3D cherry tree point cloud model. Finally, to reveal the pattern between the fruit tree canopy structure and the light distribution, a GBRT-based model for predicting the cherry tree canopy light distribution is proposed based on the established 3D cherry tree point cloud model, which takes the relative projected area features, relative surface area and relative volume characteristics of the minimum bounding box of the point cloud model as inputs and the relative light intensity as output. The experiment results show that the GBRT-based model for predicting the cherry tree canopy illumination distribution has good feasibility. The coefficient of determination between the predicted value and the actual value is 0.932, and the MAPE is 0.116, and the model can provide technical support for scientific and reasonable cherry tree pruning.