Light Detection Method Research Articles

Traffic Light Detection using Ensemble Learning by Boosting with Color-Based Data Augmentation

Recent advancements in deep neural networks have significantly improved the detection and recognition of traffic lights for advanced driver assistance systems (ADAS). Traditional methods often rely on identifying traffic light boxes and then recognizing individual signal lights, which can be problematic due to variations in bulb arrangements across different regions. To address this limitation, we propose a novel traffic light detection method that directly recognizes individual signal lights. Our two-stage approach combines data augmentation and ensemble learning to achieve high detection rates. By learning color characteristics from validation sets, we can effectively identify signal light candidates with a 97.26% accuracy rate. Subsequent classification results in a recognition accuracy of 98.6%, surpassing the performance of existing state-of-the-art traffic light detection algorithms. Code and dataset are available at https://github.com/981124/yolov7_traffic_light_detect.

Recent progress in angle-resolved photoemission spectroscopy

Abstract Angle-resolved photoemission spectroscopy (ARPES) is a well-established experimental technique that allows probing of the electronic structure of quantum materials using relatively high-energy photons. ARPES has been extensively used to study important classes of materials such as topological insulators, high-temperature superconductors, two-dimensional materials or interface systems. Although the technique was originally developed over 60 years ago, the last decade has witnessed significant advancements in instrumentation. In this review, we survey recent progress in ARPES, with a focus on developments in novel light sources and electron detection methods, which enable the expansion of ARPES into spin-, time-, or space-resolved domains. Important examples of ARPES results are presented, together with an outlook for the field.

(Invited) Detection of Wavelength Information by Filter-Free Wavelength Sensor and Its Applications

This paper introduces the wavelength and light intensity detection method using the filter-free wavelength sensor without optical components. Using a modified CMOS process, we developed a filter-free wavelength sensor with a photogate structure. The sensor can detect light intensity and wavelength without optical filters based on the dependence of the light absorption depth in silicon. Using a developed sensor, we demonstrated a wavelength, spectral shift, and light absorption detection method to apply various fields. In the future, we will continue research to realize an optical sensor system that is more compact, sensitive, and selective.

An Enhanced Deep Learning Model for Obstacle and Traffic Light Detection Based on YOLOv5

Timely detection of dynamic and static obstacles and accurate identification of signal lights using image processing techniques is one of the key technologies for guidance robots and is a necessity to assist blind people with safe travel. Due to the complexity of real-time road conditions, current obstacle and traffic light detection methods generally suffer from missed detection and false detection. In this paper, an improved deep learning model based on YOLOv5 is proposed to address the above problems and to achieve more accurate and faster recognition of different obstacles and traffic lights that the blind may encounter. In this model, a coordinate attention layer is added to the backbone network of YOLOv5 to improve its ability to extract effective features. Then, the feature pyramid network in YOLOv5 is replaced with a weighted bidirectional feature pyramid structure to fuse the extracted feature maps of different sizes and obtain more feature information. Finally, a SIoU loss function is introduced to increase the angle calculation of the frames. The proposed model’s detection performance for pedestrians, vehicles, and traffic lights under different conditions is tested and evaluated using the BDD100K dataset. The results show that the improved model can achieve higher mean average precision and better detection ability, especially for small targets.

OCDMA Codeword Switching Technique to Avoid Interference of Time-of-Flight LiDAR System for Autonomous Vehicles

The direct time-of-flight (d-ToF) technique is the most promising method for light detection and ranging (LiDAR) systems in long-range autonomous applications. However, the receiver cannot distinguish its own pulse signal from those of other LiDAR systems. This causes mutual interference between LiDAR systems, which degrades object recognition. The optical code division multiple access (OCDMA) modulation technique can be used to avoid mutual interference. However, it is difficult to secure sufficient orthogonal codes, because each laser channel uses a designated codeword. In addition, when interference occurs in a specific direction, it can occur continuously. Adversarial attacks on a LiDAR system can trick a vehicle to perform false object recognition without physical contact. This can endanger passengers, pedestrians, and other vehicles. Therefore, we propose an OCDMA codeword switching technique that can effectively solve these problems in driving environments. First, we analyzed the characteristics of optical orthogonal codes (OOC) and defined the interference generated in LiDAR systems. The proposed technique exhibits interference robustness by using a code index buffer based on differences in the received optical signal power. In addition, verification of the hardware implementation and its complexity was analyzed using LiDAR testbench and an FPGA. The interference and continuous interference of the proposed technique in various driving environments were verified using simulation model. Compared with using only a designated codeword, the proposed technique reduces interference by 82.59% and 85.51%, and continuous interference by 92.24% and 96.94% in straight-line and curved driving, respectively.

Frame-Level Rate Control for Geometry-Based LiDAR Point Cloud Compression

The state-of-the-art compression method for Light Detection And Ranging (LiDAR) point clouds is the geometry-based point cloud compression (G-PCC) standard developed by Moving Pictures Experts Group immersive media working group (MPEG-I). However, there are currently no rate control algorithms designed specifically for Geometry-based LiDAR point cloud compression (G-LPCC). In this paper, we propose the first frame-level rate control algorithm for G-LPCC. We mainly have the following contributions in our proposed rate control algorithm. First, we model the rate-distortion (R-D) relationship for both the geometry and attribute. As the geometry bitrate is mainly determined by the frame-level geometry quantizer <formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex>$Q_G$</tex></formula> , we propose a relationship between the geometry bitrate and <formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex>$Q_G$</tex></formula> . In addition, as the attribute bitrate can be influenced by both the attribute quantizer <formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex>$Q_A$</tex></formula> and <formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex>$Q_G$</tex></formula> , we build a relationship among the attribute bitrate, <formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex>$Q_G$</tex></formula> , and <formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex>$Q_A$</tex></formula> . Second, we propose a bit allocation algorithm between the geometry and attribute based on the R-D modeling. The <formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex>$Q_G$</tex></formula> and <formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex>$Q_A$</tex></formula> are modeled into a proper relationship to obtain geometry and attribute bits to achieve good R-D performance. Third, we propose using the point density of LiDAR point clouds to estimate the geometry model parameters. The point density is calculated using the average distance between each point and its nearest neighbor after excluding some noisy points. The proposed rate control algorithm is implemented in the G-PCC reference software. The experimental results show that the proposed rate control algorithm can control the bitrate accurately with satisfactory R-D performance.

Traffic Light Detection and Recognition Method Based on YOLOv5s and AlexNet

Traffic light detection and recognition technology are of great importance for the development of driverless systems and vehicle-assisted driving systems. Since the target detection algorithm has the problems of lower detection accuracy and fewer detection types, this paper adopts the idea of first detection and then classification and proposes a method based on YOLOv5s target detection and AlexNet image classification to detect and identify traffic lights. The method first detects the traffic light area using YOLOv5s, then extracts the area and performs image processing operations, and finally feeds the processed image to AlexNet for recognition judgment. With this method, the shortcomings of the single-target detection algorithm in terms of low recognition rate for small-target detection can be avoided. Since the homemade dataset contains more low-light images, the dataset is optimized using the ZeroDCE low-light enhancement algorithm, and the performance of the network model trained after optimization of the dataset can reach 99.46% AP (average precision), which is 0.07% higher than that before optimization, and the average accuracy on the traffic light recognition dataset can reach 87.75%. The experimental results show that the method has a high accuracy rate and can realize the recognition of many types of traffic lights, which can meet the requirements of traffic light detection on actual roads.

2.4 ng/√Hz low-noise fiber-optic MEMS seismic accelerometer.

This paper introduces a fiber-optic microelectromechanical system (MEMS) seismic-grade accelerometer that is fabricated by bulk silicon processing using photoresist/silicon dioxide composite masking technology. The proposed sensor is a silicon flexure accelerometer whose displacement transduction system employs a light intensity detection method based on Fabry-Perot interference (FPI). The FPI cavity is formed between the end surface of the cleaved optical fiber and the gold-surfaced sidewall of the proof mass. The proposed MEMS accelerometer is fabricated by one-step silicon deep reactive ion etching with different depths using the composite mask, among which photoresist is used as the etching-defining mask for patterning the etching area while silicon dioxide is used as the depth-defining mask. Noise evaluation experiment results reveal that the overall noise floor of the fiber-optic MEMS accelerometer is 2.4 ng/H z at 10 Hz with a sensitivity of 3165 V/g, which is lower than that of most reported micromachined optical accelerometers, and the displacement noise floor of the optical displacement transduction system is 208 fm/H z at 10 Hz. Therefore, the proposed MEMS accelerometer is promising for use in high-performance seismic exploration applications.

Dual signal light detection of beta-lactoglobulin based on a porous silicon bragg mirror

In this work, a new dual signal light detection method based on porous silicon Bragg mirror (PSBM) and biological labelling with quantum dots (QDs) is proposed for the detection of beta-lactoglobulin (β-lg). The first signal light is a probe light emitted by a laser with wavelength of 633 nm, which enters the PSBM and is reflected from the surface. The wavelength of the probe light is located at the edge of the PSBM band gap, where it has the lowest reflectivity. β-lg antibodies is labelled with CdSe/ZnS QDs and reacts with β-lg molecules have been fixed to the inner wall of the porous silicon pores. Due to the specific binding of biomolecules in PSBM, the refractive index of the device increases, resulting in the enhancement of detection reflected light. The QDs play the role of refractive index amplification. The second signal light is the fluorescence of QDs in immune reactants. QDs produce fluorescence at 630 nm when excited by a short-wavelength laser. The fluorescence signal is further enhanced by PSBM. The superimposed images of two kinds of light on the surface of PSBM are obtained by digital microscope at the same time. By calculating the average grey value change of the image before and after biological reaction, β-lg can be detected with high sensitivity. The detection limit of β-lg was 0.12 ng/mL. The experimental results showed that the PSBM-based dual signal light method could be used to detect the content of cow milk adulterated in β-lg free camel milk.

Comparison of forward and backward Lagrangian transport modelling to determine methane emissions from anaerobic digestion facilities

In biogas plants, where biological treatment of organic matter by anaerobic digestion (AD) is performed, as well as in plants for upgrading of biogas to biomethane, there might be emissions to air from different parts of the plants. Precise and comparable methods to quantify methane (CH 4 ) emissions from biogas plants are necessary to evaluate mitigation strategies and to generate more accurate emissions factors for national emission inventories in the context of the United Nations Framework Convention on Climate Change (UNFCCC) reporting. The main objective of this study was to provide recommendations for the measurement and modelling procedures of inverse dispersion modelling (IDM) to assure comparability of CH 4 emissions among diverse approaches and AD facilities. Two Lagrangian stochastic dispersion models were used operating in forward (LASAT) and backward (WindTrax) mode based on open-path concentration and meteorological data acquired by three international measurement teams at two biogas plants. The sensitivity analysis of the modelling systems regarding input parameters and setups (e.g. source configuration, terrain, sampling distance from the site, different combinations of wind data) showed that in WindTrax (backward mode) the measurement speed of meteorological parameters (via three-dimensional ultrasonic anemometer) had the largest influence on the calculated emission estimates, while in LASAT (forward mode) the assumption of the source configuration greatly affected the flux estimates. The used concentration data (e.g. location of observations, measurement mode of background concentration) was critically important to the success of IDM. The CH 4 emission rates from the AD facility in flat terrain (plant 1) calculated with both Lagrangian models by IDM showed good agreement with the DIAL (Differential Absorption Light Detection And Ranging) method and methane release tests (deviation in the range of 10–20%) when using best fit configurations (e.g. volume source in LASAT, area source in WindTrax, optimal measurement fetch). In moderately complex terrain (plant 2), the retrieval rates of controlled CH 4 releases, and thus the certainty of flux estimates of both dispersion models tended to decrease without the use of a terrain model. • First comparison of emission results inferred with LASAT and WindTrax. • Concentration and meteorological data obtained by three independent measurement teams. • Evaluation of sensitivity of the modelling system to input parameters and setups. • Recommendations for measurement and modelling procedure. • Uncertainty of ±10–20% for both models in flat terrains using best fit configurations.

Novel rotor effective wind speed estimation method for light detection and ranging application

The ‘Cyclops’ effect of the light detection and ranging (LiDAR) system means that the LiDAR system can only measure wind speed at one point in space at a certain moment. However, for the purposes of wind turbine control, considering the wind information at the rotor plane with time stamps can be more precise. The wind speed attenuates due to the induction zone; however, Taylor's frozen hypothesis is commonly used in the application of LiDAR for the rotor effective wind speed estimation. The wind turbine is controlled directly by LiDAR measured data with constant time delay, which weakens LiDAR's effectiveness. In this paper, a novel LiDAR data pre-processing method is demonstrated. The Medici induction zone model is further refined with initial wind speed and different measured distances for accurate estimation. Furthermore, it makes online variable time delay of LiDAR data computation possible with the solution of the separated differential equation. Finally, the novel method is fully verified through field test results. The results show that the initial wind speed affected the attenuation factor within 1.4 times rotor radius and the error between the experimental value and the theoretical value is within 0.1 m/s.

A novel fast classification filtering algorithm for LiDAR point clouds based on small grid density clustering

Clustering filtering is usually a practical method for light detection and ranging (LiDAR) point clouds filtering according to their characteristic attributes. However, the amount of point cloud data is extremely large in practice, making it impossible to cluster point clouds data directly, and the filtering error is also too large. Moreover, many existing filtering algorithms have poor classification results in discontinuous terrain. This article proposes a new fast classification filtering algorithm based on density clustering, which can solve the problem of point clouds classification in discontinuous terrain. Based on the spatial density of LiDAR point clouds, also the features of the ground object point clouds and the terrain point clouds, the point clouds are clustered firstly by their elevations, and then the plane point clouds are selected. Thus the number of samples and feature dimensions of data are reduced. Using the DBSCAN clustering filtering method, the original point clouds are finally divided into noise point clouds, ground object point clouds, and terrain point clouds. The experiment uses 15 sets of data samples provided by the International Society for Photogrammetry and Remote Sensing (ISPRS), and the results of the proposed algorithm are compared with the other eight classical filtering algorithms. Quantitative and qualitative analysis shows that the proposed algorithm has good applicability in urban areas and rural areas, and is significantly better than other classic filtering algorithms in discontinuous terrain, with a total error of about 10%. The results show that the proposed method is feasible and can be used in different terrains.

Light Detection and Ranging (LiDAR)-Assisted Detection of Rock Outcrops in Appalachian Hardwood Forests

Abstract The identification of small habitat features embedded within forest ecosystems is a challenge for many wildlife inventory and monitoring programs, especially for those involving rock outcrop specialist taxa. Rock outcrops are often difficult to remotely detect in dense Appalachian hardwood forests, as most outcrops remain hidden under the forest canopy and therefore invisible when relying on aerial orthoimagery to pinpoint habitat features. We investigated the ability for light detection and ranging point cloud data to identify small rock outcrops during the environmental assessment phase of a proposed management project on the Jefferson National Forest in Virginia. We specifically compared this approach with the visual identification of rock outcrops across the same area using aerial orthoimagery. Our light detection and ranging-based approach identified three times as many rock outcrop sites as aerial orthoimagery, resulting in the field verification of four times as many previously unknown populations of green salamanders Aneides aeneus (a rock outcrop specialist amphibian of high conservation concern) than would have been possible if relying on aerial orthoimagery alone to guide surveys. Our results indicate that light detection and ranging-based methods may provide an effective, efficient, and low-error approach that can remotely identify below-canopy rock outcrops embedded within Appalachian forests, especially when researchers lack pre-existing knowledge of local terrain and the location of habitat features.

Stochastic light concentration from 3D to 2D reveals ultraweak chemi- and bioluminescence

For countless applications in science and technology, light must be concentrated, and concentration is classically achieved with reflective and refractive elements. However, there is so far no efficient way, with a 2D detector, to detect photons produced inside an extended volume with a broad or isotropic angular distribution. Here, with theory and experiment, we propose to stochastically transform and concentrate a volume into a smaller surface, using a high-albedo Ulbricht cavity and a small exit orifice through cavity walls. A 3D gas of photons produced inside the cavity is transformed with a 50% number efficiency into a 2D Lambertian emitting orifice with maximal radiance and a much smaller size. With high-albedo quartz-powder cavity walls (rho =99.94%), the orifice area is 1/(1-rho )approx 1600 times smaller than the walls’ area. When coupled to a detectivity-optimized photon-counter (mathcal{D}=0.015,{text{photon}}^{-1},{text{s}}^{1/2}text{ cm}) the detection limit is 110;{text{photon}};{text{s}}^{ - 1} ;{text{L}}^{ - 1}. Thanks to this unprecedented sensitivity, we could detect the luminescence produced by the non-catalytic disproportionation of hydrogen peroxide in pure water, which has not been observed so far. We could also detect the ultraweak bioluminescence produced by yeast cells at the onset of their growth. Our work opens new perspectives for studying ultraweak luminescence, and the concept of stochastic 3D/2D conjugation should help design novel light detection methods for large samples or diluted emitters.

Micro/Nano profile measurement by structured illumination microscopy utilizing time-domain phase-shift technique

Aiming at the technical difficulties in the rapid detection and reconstruction of three-dimensional micro-nano devices that are difficult to achieve both high precision and high speed, this paper proposes a structured light detection method based on time-domain phase shift technology. The measured light is modulated by a spatial light modulator, and the time-domain phase shift technology is further employed to realize the detection and reconstruction of three-dimensional micro-nano devices. Compared with the traditional structured light detection method, this technology uses the spatial light modulator to measure the phase shift while the sample is scanned axially, so as to ensure the measurement accuracy and improve the measurement efficiency. By analyzing the measurement data, this method can quickly realize three-dimensional shape detection and reconstruction, and the measurement accuracy can be better than 10 nm.

A new approach for roof segmentation from airborne LiDAR point clouds

ABSTRACT Accurate roof segmentation is one of the key steps for automatically constructing three-dimensional (3-D) building models. Building roofs can differ significantly in terms of their size, shape complexity, and number, rendering many existing airborne Light Detection And Ranging (LiDAR) roof segmentation methods ineffective. Thus, the applicability and precision of these methods need to be improved. For this purpose, this paper proposes a new roof segmentation method for airborne LiDAR point clouds. The proposed method integrates a novel region growing strategy and RANdom SAmple Consensus (RANSAC), applying these approaches to extract several reliable roof patches and then performing an iterative process to merge roof patches based on their parameters and the concept of inlier selection of RANSAC. Finally, unsegmented points and segmentation results are refined by voting in a local neighbourhood. The experimental results show that the proposed method can effectively segment the roofs of buildings with different complexity and sizes. As the basic evaluation primitive, the average segmentation correctness was found to be 95.67 and 97.85% when using a roof and a single point, respectively, which can provide reliable information for applications, such as 3-D building model reconstruction.

Research on Coherent Light detection Method Based on Phase Control of Fiber Delay Line

With the system modeling and simulation, analyzed the mechanisms of signal transmission and storage, and phase-controlling, and researched the relationship between time-delay and phase-delay. The effect of optical path difference on optical phase-matching is investigated in time domain and frequency domain. The results shows that, the signal power will obtain maximum after coherent mixing when the phase between signal light and reference light is 2nπ(n=0, 1, 2……); the signal power will obtain minimum when it is (2n+1)π(n=0, 1, 2……), and the mixing signal of other phase relationship will vary in this range. And it is proved that the time delay of optical fiber delay line could effectively compensate the phase delay which generated in the transmission and a phase controlling of the signal transmission could be achieved.

Mapless LiDAR Navigation Control of Wheeled Mobile Robots Based on Deep Imitation Learning

This paper addresses the problems related to the mapless navigation control of wheeled mobile robots based on deep learning technology. The traditional navigation control framework is based on a global map of the environment, and its navigation performance depends on the quality of the global map. In this paper, we proposes a mapless Light Detection and Ranging (LiDAR) navigation control method for wheeled mobile robots based on deep imitation learning. The proposed method is a data-driven control method that directly uses LiDAR sensors and relative target position for mobile robot navigation control. A deep convolutional neural network (CNN) model is proposed to predict motion control commands of the mobile robot without the requirement of the global map to achieve navigation control of the mobile robot in unknown environments. While collecting the training dataset, we manipulated the mobile robot to avoid obstacles through manual control and recorded the raw data of the LiDAR sensor, the relative target position, and the corresponding motion control commands. Next, we applied a data augmentation method on the recorded samples to increase the number of training samples in the dataset. In the network model design, the proposed CNN model consists of a LiDAR CNN module to extract LiDAR features and a motion prediction module to predict the motion behavior of the robot. In the model training phase, the proposed CNN model learns the mapping between the input sensor data and the desired motion behavior through end-to-end imitation learning. Experimental results show that the proposed mapless LiDAR navigation control method can safely navigate the mobile robot in four unseen environments with an average success rate of 75%. Therefore, the proposed mapless LiDAR navigation control system is effective for robot navigation control in an unknown environment without the global map.

Identifying the Biological Characteristics Associated with Oviposition Behavior of Tea Leafhopper Empoasca onukii Matsuda Using the Blue Light Detection Method.

Simple SummaryThe tea leafhopper (Empoasca onukii Matsuda) is currently one of the most threatening pests in tea gardens in China. To locate and count tea leafhopper eggs, stereomicroscopy is a conventional method by dissecting the tender tissues, which is both time- and labor-consuming. The scarcity of a verified method to directly observe and investigate intact eggs within tea shoots impedes the research efforts to test the oviposition behavior of E. onukii. Herein, comparing against the stereomicroscope detection method (SMDM), we evaluated the blue light detection method (BLDM), a technique recently developed for other species in detecting E. onukii eggs directly and non-destructively within the tender shoot for four tea cultivars. The conclusion indicated that BLDM could correctly measure the egg laying quantity of E. onukii on intact tea shoots, and its accuracy was not affected by both tea cultivars and egg density in the tender shoot. Furthermore, the biological characteristics concerning the oviposition behaviors that have rarely been reported previously for E. onukii were investigated using the BLDM. Our findings provide insights for the basic research and theoretical evidence, and allow the follow-up studies for the strategy and mechanism associated with the egg laying behavior of E. onukii.Tea leafhopper (Empoasca onukii Matsuda) is amongst the key pests in tea plantations around the East Asian region. Stereomicroscopy is a conventional method used for detecting tea leafhopper eggs by dissecting the tender tissues. However, there is a need for a faster and more efficient method to directly observe and investigate intact eggs within tea shoots. The absence of a proven method limits research efforts for determining the oviposition behavior of E. onukii. Herein, we applied the blue light detection method (BLDM), a technique recently developed for other species, in order to detect E. onukii eggs directly and non-destructively within the tender shoot. In addition, we compared BLDM against the traditional stereomicroscope detection method (SMDM) for four tea cultivars. Notably, our results revealed that BLDM was precise and effective in measuring the egg laying quantity of E. onukii on intact tea shoots. Neither tea cultivars nor egg density in the tender shoot significantly affected the accuracy of BLDM. Furthermore, biological characteristics that have rarely been reported previously for E. onukii were investigated using the BLDM, including zygote duration, ovipositional rhythm, egg distribution within the tender shoot, and in different leaf positions, numbers of eggs laid by a single female daily, and laid by the entire generation. Therefore, these findings provide insights into the basic and theoretical evidence for the strategy and mechanism associated with the oviposition behavior of E. onukii.

Individual Tree Crown Segmentation of a Larch Plantation Using Airborne Laser Scanning Data Based on Region Growing and Canopy Morphology Features

The detection of individual trees in a larch plantation could improve the management efficiency and production prediction. This study introduced a two-stage individual tree crown (ITC) segmentation method for airborne light detection and ranging (LiDAR) point clouds, focusing on larch plantation forests with different stem densities. The two-stage segmentation method consists of the region growing and morphology segmentation, which combines advantages of the region growing characteristics and the detailed morphology structures of tree crowns. The framework comprises five steps: (1) determination of the initial dominant segments using a region growing algorithm, (2) identification of segments to be redefined based on the 2D hull convex area of each segment, (3) establishment and selection of profiles based on the tree structures, (4) determination of the number of trees using the correlation coefficient of residuals between Gaussian fitting and the tree canopy shape described in each profile, and (5) k-means segmentation to obtain the point cloud of a single tree. The accuracy was evaluated in terms of correct matching, recall, precision, and F-score in eight plots with different stem densities. Results showed that the proposed method significantly increased ITC detections compared with that of using only the region growing algorithm, where the correct matching rate increased from 73.5% to 86.1%, and the recall value increased from 0.78 to 0.89.