Abstract:The recent trend of fusing complementary data from LiDARs and cameras for more accurate perception has made the extrinsic calibration between the two sensors critically important. Indeed, to align the sensors spatially for proper data fusion, the calibration process usually involves estimating the extrinsic parameters between them. Traditional LiDAR-camera calibration methods often depend on explicit targets or human intervention, which can be prohibitively expensive and cumbersome. Recognizing these weaknesse… Show more
“…These methods are convenient and can be performed online. Our team conducted a careful survey Li et al (2022) of automatic targetless camera-LiDAR calibration.…”
Section: Lidar Camera Calibrationmentioning
confidence: 99%
“…These methods are convenient and can be performed online. Our team conducted a careful survey Li et al (2022) of automatic targetless camera-LiDAR calibration.Figure 18.Velo2Cam Beltrán et al camera-LiDAR calibration. Up-Left : special calibration board, project LiDAR point cloud to the image.…”
Section: Sensor Synchronization and Calibrationmentioning
In this paper, we present the USTC FLICAR Dataset, which is dedicated to the development of simultaneous localization and mapping and precise 3D reconstruction of the workspace for heavy-duty autonomous aerial work robots. In recent years, numerous public datasets have played significant roles in the advancement of autonomous cars and unmanned aerial vehicles (UAVs). However, these two platforms differ from aerial work robots: UAVs are limited in their payload capacity, while cars are restricted to two-dimensional movements. To fill this gap, we create the “Giraffe” mapping robot based on a bucket truck, which is equipped with a variety of well-calibrated and synchronized sensors: four 3D LiDARs, two stereo cameras, two monocular cameras, Inertial Measurement Units (IMUs), and a GNSS/INS system. A laser tracker is used to record the millimeter-level ground truth positions. We also make its ground twin, the “Okapi” mapping robot, to gather data for comparison. The proposed dataset extends the typical autonomous driving sensing suite to aerial scenes, demonstrating the potential of combining autonomous driving perception systems with bucket trucks to create a versatile autonomous aerial working platform. Moreover, based on the Segment Anything Model (SAM), we produce the Semantic FLICAR dataset, which provides fine-grained semantic segmentation annotations for multimodal continuous data in both temporal and spatial dimensions. The dataset is available for download at: https://ustc-flicar.github.io/ .
“…These methods are convenient and can be performed online. Our team conducted a careful survey Li et al (2022) of automatic targetless camera-LiDAR calibration.…”
Section: Lidar Camera Calibrationmentioning
confidence: 99%
“…These methods are convenient and can be performed online. Our team conducted a careful survey Li et al (2022) of automatic targetless camera-LiDAR calibration.Figure 18.Velo2Cam Beltrán et al camera-LiDAR calibration. Up-Left : special calibration board, project LiDAR point cloud to the image.…”
Section: Sensor Synchronization and Calibrationmentioning
In this paper, we present the USTC FLICAR Dataset, which is dedicated to the development of simultaneous localization and mapping and precise 3D reconstruction of the workspace for heavy-duty autonomous aerial work robots. In recent years, numerous public datasets have played significant roles in the advancement of autonomous cars and unmanned aerial vehicles (UAVs). However, these two platforms differ from aerial work robots: UAVs are limited in their payload capacity, while cars are restricted to two-dimensional movements. To fill this gap, we create the “Giraffe” mapping robot based on a bucket truck, which is equipped with a variety of well-calibrated and synchronized sensors: four 3D LiDARs, two stereo cameras, two monocular cameras, Inertial Measurement Units (IMUs), and a GNSS/INS system. A laser tracker is used to record the millimeter-level ground truth positions. We also make its ground twin, the “Okapi” mapping robot, to gather data for comparison. The proposed dataset extends the typical autonomous driving sensing suite to aerial scenes, demonstrating the potential of combining autonomous driving perception systems with bucket trucks to create a versatile autonomous aerial working platform. Moreover, based on the Segment Anything Model (SAM), we produce the Semantic FLICAR dataset, which provides fine-grained semantic segmentation annotations for multimodal continuous data in both temporal and spatial dimensions. The dataset is available for download at: https://ustc-flicar.github.io/ .
“…Targetless methods can be roughly classified into four groups, that is, information-theoretic, motion-based, feature-based, and deep-learning methods. Informationtheoretic methods estimate the extrinsic parameters by maximizing the similarity transformation between cameras and LiDAR sensors [20,31]. Pandey et al [32] used the correlation between camera image pixel grayscale values and LiDAR point-cloud reflectivity to optimize the estimation of extrinsic parameters by maximizing the mutual information.…”
Section: Related Workmentioning
confidence: 99%
“…Special calibration sites are required, which can be extremely vulnerable to artificial and noise interference. By contrast, motion-based calibration methods can automatically estimate the extrinsic parameters between cameras and LiDAR sensors without requiring structured targets; however, their calibration accuracy needs to be further improved [20].…”
With the continuous development and popularization of sensor-fusion technology for mobile robots, the application of camera and light detection and ranging (LiDAR) fusion perception has become particularly important. Moreover, the calibration of extrinsic parameters between the camera and LiDAR is a crucial prerequisite for fusion. Although traditional target-based calibration methods have been widely adopted, their cumbersome operation and high costs necessitate the development of more efficient and flexible calibration methods. To address this problem, this study proposed a two-stage calibration method based on motion and edge matching. In the first stage, the preliminary estimation of the extrinsic parameters between the camera and LiDAR was performed by matching visual odometry and LiDAR odometry using a hand–eye target method. In the second stage, the calibration results from the first stage were further refined by matching the image edges and discontinuous depth point clouds. The calibration system was then tested in both simulated and actual environments. The experimental results showed that this method, which did not require specially structured targets, could achieve highly flexible and robust automated calibration. Compared to other advanced methods, the accuracy of the proposed method was higher.
“…The calibration of multi-sensor systems consisting of similar sensors has been studied by many scholars (e.g. LIDAR to camera, radar to camera, camera-IMU [6,7]), and in particular, the calibration methods between LIDAR and camera have reached a mature level [8,9]. The high density of the LIDAR point cloud allows for the extraction of distinctive features from specific geometric objects within the target point cloud (a special calibration target is commonly employed for this purpose).…”
Most intelligent transportation and autonomous driving systems use the combination of millimeter-wave (MMW) radar and camera to achieve strong perception, and correct extrinsic calibration is a prerequisite for sensor fusion. Most prior calibration methods rely on specific calibration environment, resulting in low calibration efficiency, and are unsuitable for practical scenarios. This paper proposes a progressive and efficient extrinsic calibration method for 3D MMW radar and camera, which only requires testers to walk around the testing range with the calibration target, and the progressive process of extrinsic parameters regression is visualized. The proposed method has been tested on the View-of-Delft dataset and in the real world, and the results show that the method proposed in this paper can converge the calibrated extrinsic parameters quickly and has strong robustness to the noise present during the testing process. Compared to EPNP, LM, P3P (based on RANSAC), and LM (based on RANAC), our proposed calibration method demonstrates a smaller re-projection error and higher accuracy in terms of extrinsic parameters. All results indicate that our calibration method has good accuracy and efficiency for practical calibration scenarios.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
