• IEMEK Journal of Embedded Systems and Applications
• /
• v.15 no.5
• /
• pp.215-225
• /
• 2020

Light detection and ranging (LiDAR) sensors detect the distance of the surrounding environment and objects. Conventional LiDAR sensors require a certain amount of a power because they detect objects by transmitting lasers at a regular interval depending on a constant resolution. The constant power consumption from operating multiple LiDAR sensors is detrimental to autonomous and electric vehicles using battery power. In this paper, we propose two algorithms that improve the inefficient power consumption during the constant operation of LiDAR sensors. LiDAR sensors with algorithms efficiently reduce the power consumption in two ways: (a) controlling the resolution to vary the laser transmission period (T_P) of a laser diode (LD) depending on the vehicle's speed and (b) reducing the static power consumption using a sleep mode depending on the surrounding environment. A proposed LiDAR sensor with a resolution control algorithm reduces the power consumption of the LD by 6.92% to 32.43% depending on the vehicle's speed, compared to the maximum number of laser transmissions (N_x·max). The sleep mode with a surrounding environment-sensing algorithm reduces the power consumption by 61.09%. The proposed LiDAR sensor has a risk factor for 4-cycles that does not detect objects in the sleep mode, but we consider it to be negligible because it immediately switches to an active mode when a change in surrounding conditions occurs. The proposed LiDAR sensor was tested on a commercial processor chip with the algorithm controlling the resolution according to the vehicle's speed and the surrounding environment.

• Journal of the Korean Geophysical Society
• /
• v.9 no.1
• /
• pp.7-19
• /
• 2006

Laser scanning is a new technology for obtaining Digital Surface Models(DSM) of the earth surface.It is a fast method for sampling the earth surface with high density and high point accuracy. This paper is for buildings extraction from LiDAR points data. The core part of building construction is based on a parameters filter for distinguishing between terrain and non-terrain laser points. The 3D geometrical properties of the building facades are obtained based on plane fitting using least-squares adjustment. The reconstruction part of the procedure is based on the adjacency among the roof facades. Primitive extraction and facade intersections are used for building reconstruction. For overcome the difficulty just reconstruct of laser points data used with digital camera images. Also, 3D buildings of city area reconstructed using digital map. Finally, In this paper show 3D building Modeling using digital map and LiDAR data.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.29 no.4
• /
• pp.429-438
• /
• 2011

LiDAR technology is a combination of laser ranging, satellite positioning technology and digital image technology for study and determination with high accuracy of the true earth surface features in 3 D. Laser scanning data is typically a points cloud on the ground, including coordinates, altitude and intensity of laser from the object on the ground to the sensor (Wehr & Lohr, 1999). Data from laser scanning can produce products such as digital elevation model (DEM), digital surface model (DSM) and the intensity data. In Vietnam, the LiDAR technology has been applied since 2005. However, the application of LiDAR in Vietnam is mostly for topological mapping and DEM establishment using point cloud 3D coordinate. In this study, another application of LiDAR data are present. The study use the intensity image combine with some other data sets (elevation data, Panchromatic image, RGB image) in Bacgiang City to perform land cover classification using neural network method. The results show that it is possible to obtain land cover classes from LiDAR data. However, the highest accurate classification can be obtained using LiDAR data with other data set and the neural network classification is more appropriate approach to conventional method such as maximum likelyhood classification.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2004.04a
• /
• pp.383-388
• /
• 2004

The fusion of a different kind sensor is fusion of the obtained data by the respective independent technology. This is a important technology for the construction of 3D spatial information. particularly, information is variously realized by the fusion of LiDAR and mobile scanning system and digital map, fusion of LiDAR data and high resolution, LiDAR etc. This study is to generate union DEM and digital ortho image by the fusion of LiDAR data and high resolution image and monitor precisely topology, building, trees etc in urban areas using the union DEM and digital ortho image. using only the LiDAR data has some problems because it needs manual linearization and subjective reconstruction.

• Journal of Korean Society for Geospatial Information Science
• /
• v.24 no.2
• /
• pp.113-120
• /
• 2016

The necessity of maritime sector for continuous management, accurate and update location information such as seabed shape and location, research on airborne LiDAR bathymetry surveying techniques are accelerating. Airborne LiDAR systems consist of a scanner and GPS/INS. The location accuracy of 3D point data obtained by a LiDAR system is determined by external orientation parameters. However, there are problems in the synchronization between sensors should be performed due to a variety of sensor combinations and arrangement. To solve this issue, system calibration should be conducted. Therefore, this study evaluates the system verification methods, processes, and operation techniques.

• Korean Journal of Construction Engineering and Management
• /
• v.24 no.2
• /
• pp.70-78
• /
• 2023

Inclinometer has several problems of 1)difficulty installing inclinometer casing, 2) measuring 2D local lateral displacement of retaining wall, 3) measurement by manpower. To solve such problems, a 2D LiDAR sensor-based retaining wall displacement measurement system was developed in previous studies. The purpose of this study is to select a displacement analysis algorithm to be applied in the retaining wall displacement measurement system. As a result of the displacement analysis algorithm selection, the M3C2 (Multiple Model to Model Cloud Comparison) algorithm with a displacement estimation error of 2mm was selected as the displacement analysis algorithm. If the M3C2 algorithm is applied in the system and the reliability of the displacement analysis result is secured through several field experiments. Convenient management of the displacement for the retaining wall is possible in comparison with the current measurement management.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.14 no.1
• /
• pp.1-9
• /
• 2019

In this paper, we propose a method of generating a 2D gray image from LiDAR 3D reflection intensity. The proposed method uses the Fully Convolutional Network (FCN) to generate the gray image from 2D reflection intensity which is projected from LiDAR 3D intensity. Both encoder and decoder of FCN are configured with several convolution blocks in the symmetric fashion. Each convolution block consists of a convolution layer with $3{\times}3$ filter, batch normalization layer and activation function. The performance of the proposed method architecture is empirically evaluated by varying depths of convolution blocks. The well-known KITTI data set for various scenarios is used for training and performance evaluation. The simulation results show that the proposed method produces the improvements of 8.56 dB in peak signal-to-noise ratio and 0.33 in structural similarity index measure compared with conventional interpolation methods such as inverse distance weighted and nearest neighbor. The proposed method can be possibly used as an assistance tool in the night-time driving system for autonomous vehicles.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.716-717
• /
• 2023

최근 자율주행 기술이 큰 주목을 받고 있지만 고가의 센서를 필요로 하기 때문에 연구 및 상용화에 큰 어려움을 겪고 있다. 따라서 본 논문은 쉽게 사용 가능한 딥러닝 2D 객체 인식 모델과 범용 태블릿에 탑재된 저비용 LiDAR 센서를 이용하여 실시간 3D 객체 탐지가 가능한 시스템을 개발한다. 개발된 시스템을 실제 1/10 크기의 차량 모델에 적용하여 테스트해본 결과 개발 용이성과 정확도 측면에서 자율주행을 위한 저비용 센서로 충분히 활용될 가능성이 있음을 확인하였다.

• The Journal of Korea Robotics Society
• /
• v.18 no.3
• /
• pp.346-351
• /
• 2023

With the release of numerous open driving datasets, the demand for domain adaptation in perception tasks has increased, particularly when transferring knowledge from rich datasets to novel domains. However, it is difficult to solve the change 1) in the sensor domain caused by heterogeneous LiDAR sensors and 2) in the environmental domain caused by different environmental factors. We overcome domain differences in the semi-supervised setting with 3-stage model parameter training. First, we pre-train the model with the source dataset with object scaling based on statistics of the object size. Then we fine-tine the partially frozen model weights with copy-and-paste augmentation. The 3D points in the box labels are copied from one scene and pasted to the other scenes. Finally, we use the knowledge distillation method to update the student network with a moving average from the teacher network along with a self-training method with pseudo labels. Test-Time Augmentation with varying z values is employed to predict the final results. Our method achieved 3rd place in ECCV 2022 workshop on the 3D Perception for Autonomous Driving challenge.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.5
• /
• pp.425-433
• /
• 2020

Three-dimensional data has been used for different applications such as robotics, building reconstruction, and so on. 3D data can be generated from an optical camera or a laser scanner. Especially, a wearable multi-sensor system including the above-mentioned sensors is an optimized structure that can overcome the drawbacks of each sensor. After finding the geometric relationships between sensors, georeferencing of the datasets acquired from the moving system, should be carried out. Especially, in an indoor environment, error propagation always causes problem in the georeferencing process. To improve the accuracy of this process, other sources of data were used to combine with LiDAR (Light Detection and Ranging) data, and various registration methods were also tested to find the most suitable way. More specifically, this paper proposed a new process of NDT (Normal Distribution Transform) to register the LiDAR point cloud, with additional information from other sensors. For real experiment, a wearable mapping system was used to acquire datasets in an indoor environment. The results showed that applying the new process of NDT and combining LiDAR data with IMU (Inertial Measurement Unit) information achieved the best result with the RMSE 0.063 m.