A real-time curb detection and tracking method for UGVs by using a 3D-LIDAR sensor

Environment perception is an essential component in autonomous driving technology. Curb is one of the most prominent features on an urban road, which defines the boundary of a road surface. An intersection is a junction of two or more roads, appearing where no curb exists. Intersection recognition and curb detection are significant in environment perception which ensure the performance of Unmanned Ground Vehicles (UGVs). In this paper, a novel double layer beam model is proposed to recognise the intersection shape and classify the road type in front of the UGV, and then based on the current road type and spatial features, a real-time road boundary detection algorithm is proposed to extract the curb position. The performance of the proposed method is verified through extensive experiments with a UGV autonomously driving on campus roads. The experimental results demonstrate the accurate and robust performance of the proposed algorithm.

Road boundary detection is an important part of the perception of the autonomous driving. It is difficult to detect road boundaries of unstructured roads because there are no curbs. There are no clear boundaries on mine roads to distinguish areas within the road boundary line and areas outside the road boundary line. This paper proposes a real-time road boundary detection and tracking method by a 3D-LIDAR sensor. The road boundary points are extracted from the detected elevated point clouds above the ground point cloud according to the spatial distance characteristics and the angular features. Road tracking is to predict and update the boundary point information in real-time, in order to prevent false and missed detection. The experimental verification of mine road data shows the accuracy and robustness of the proposed algorithm.

In this paper we present a robust and real-time hand detection and tracking method. A new edge feature descriptor (HOG-Like feature descriptor) is first proposed, and used for the hand detection and tracking. The hand detection method is based on the AdaBoost and HOG-Like feature. A cascade framework is used to speed up. A detailed study was developed to select the training parameters. The HOG-Like feature can also be used for other object detection, such as president detection. When tracking the hand a six parameters-state and motion model is used for predicting the hand's location. In this way it reduces the computer time radically. The experimental result demonstrates that the method can successfully detect the hand and track it in real-time. The hand detection and tracing can be used hand-based Human-Computer Interface.

Deep Learning is the latest research achievement in the field of Artificial Intelligence. To detect and identify the state of circuit breaker in ambient air automatic monitor station, Deep Learning was proposed to realize the circuit breaker state recognition in real-time. The Deep Convolutional Neural Network was used to construct the state detection and identification model of the circuit breaker and provided the detection process. The remote monitoring system of ambient air automatic monitor station and inspection data were used to build the experimental data platform, with the circuit breaker state recognition data was acquired from the multiple ambient air automatic monitor stations. Through training the model with the Deep Learning, the experimental results showed that the circuit breaker state detection and identification method have a simple recognition process and high accuracy. The real-time Detection and Identification function of the circuit breaker state was realized, meanwhile, the assistant decision-making function was provided to the ambient air automatic monitor station.

As one of the most commonly used acoustic systems in seabed surveys, the altitude of the side scan sonar from the seafloor is always difficult to determine, especially when raw signal levels and gain information are unavailable. The inaccurate sonar altitudes would limit the applications of sonar image geocoding, target detection, and sediment classification. The sonar altitude can be obtained by using bottom tracking methods, but traditional methods often require manual thresholds or complex post-processing procedures, which cannot ensure accurate and real-time bottom tracking. In this paper, a real-time bottom tracking method of side scan data is proposed based on a one-dimensional convolution neural network. First, according to the characteristics of side scan backscatter strength sequences, positive (bottom sequences) and negative (water column and seabed sequences) samples are extracted to establish the sample sets. Second, a one-dimensional convolution neural network is carefully designed and trained by using the sample set to recognize the bottom sequences. Third, a complete processing procedure of the real-time bottom tracking method is established by traversing each side scan ping data and recognizing the bottom sequences. The auxiliary methods for improving real-time performance and sample data augmentation are also explained in detail. The proposed method is implemented on the measured side scan data from the marine area in Meizhou Bay. The trained network model achieves a 100% recognition of the initial sample set as well as 100% bottom tracking accuracy of the training survey line. The average bottom tracking accuracy of the testing survey lines excluding missed pings reaches 99.2%. By comparison with multi-beam bathymetric data and the statistical analysis of real-time performance, the experimental results prove the validity and accuracy of the proposed real-time bottom tracking method.

Multiple Road-Objects Detection and Tracking for Autonomous Driving

As the research hotspot of intelligent transportation system (ITS), unmanned ground vehicle (UGV) with high intelligence is able to reduce the probability of traffic accidents and traffic congestion, and improve the efficiency of urban transportation system. Environmental perception is one of the key research topics in the research of key technologies of UGV. The campus transportation environment, as a simple version of the urban transportation environment, needs to perceive as much traffic information as the urban traffic environment. At the same time, the geographic information system (GIS) has capabilities of strong geographical information storage and management, which can play a critical role in the environmental perception of UGV. In this paper, we study the autonomous driving of unmanned ground vehicle in the campus traffic environment, and the construction method of GIS database is proposed for the perception demand of UGV in the traffic environment of campus. Then, according to the GIS database, autonomous navigation control of UGV is carried out to verify its applicability and effectiveness. After testing, the GIS database proposed in this paper can assist the autonomous driving of UGV well and complete the driving tasks in the campus environment.

The unmanned ground vehicle is supposed to replace humans for various applications in both civilian and military area, including transport, delivery, shuttle, clean, patrol, scout, and battle. It has been widely expected that the unmanned ground vehicle will greatly change the human life and the land combat form in the near future. The key techniques of the unmanned ground vehicle are environment perception, motion planning, chassis dynamics control, and cloud control. In this paper, the state of the art of the development of the military and civilian unmanned ground vehicle is introduced, and many classic ones are reviewed in detail in different application categories. The overall design and X-by-wire dynamics control technique of the civilian and military unmanned ground vehicle are reviewed. The X-by-wire technique plays an important role in improving the maneuverability, mobility, and handling performance of the unmanned ground vehicle. Therefore, the chassis dynamics control is considered as a core technique of the X-by-wire unmanned ground vehicle. In addition, as a research trend of the unmanned ground vehicle dynamics control, the cloud-based dynamics control approach of future unmanned ground vehicle based on big data and cloud control techniques is described according to the authors’ work.

Here, an adaptive real-time 3D single particle tracking method is proposed, which is capable of capturing heterogeneous dynamics. Using a real-time measurement of a rapidly diffusing particle's positional variance, the 3D precision adaptive real-time tracking (3D-PART) microscope adjusts active-feedback parameters to trade tracking speed for precision on demand. This technique is demonstrated first on immobilized fluorescent nanoparticles, with a greater than twofold increase in the lateral localization precision (≈25 to ≈11 nm at 1 ms sampling) as well as a smaller increase in the axial localization precision (≈ 68 to ≈45 nm). 3D-PART also shows a marked increase in the precision when tracking freely diffusing particles, with lateral precision increasing from ≈100 to ≈70 nm for particles diffusing at 4 µm2 s-1 , although with a sacrifice in the axial precision (≈250 to ≈350 nm). This adaptive microscope is then applied to monitoring the viral first contacts of virus-like particles to the surface of live cells, allowing direct and continuous measurement of the viral particle at initial contact with the cell surface.

Aiming at the real-time tracking problem of multiple unmanned aerial vehicles (UAVs) based on video under fog conditions, we propose a multitarget real-time tracking method that combines the Deepsort algorithm with detection based on improved dark channel defogging and improved You Only Look Once version 5 (YOLOv5) algorithm. The contributions of this paper are as follows: 1. For the multitarget tracking problem under fog interference, a multialgorithm combination method is proposed. 2. By optimizing dark channel defogging, the complexity of the original algorithm is reduced from On2 to On, which simplifies the processing time of the defogging algorithm. 3. The YOLOv5 network structure is optimized so that the network can synchronously reduce the detection time while maintaining high-precision detection. 4. The amount of algorithm processing through image size compression is reduced, and the real-time performance under high-precision tracking is improved. In the experiments conducted, the proposed method improved tracking precision by 36.1% and tracking speed by 39%. The average time of tracking per image frame was 0.036s, satisfying the real-time tracking of multiple UAVs in foggy weather.

Currently, the existing fault detection methods have problems in that the detection results are not in line with reality and the detection accuracy is too low when detecting the grounding circulation fault of transmission cables. This paper introduces the wavelet energy spectrum of module components to design and study the real-time fault detection method of grounding the circulating current of the transmission cable. In this study, the wavelet-based detection function that meets the requirements of fault detection is selected. On this basis, the traveling wave fault features are extracted by using the wavelet energy spectrum of the module component. Finally, the fault detection signal is decomposed in real-time, and the fault detection is realized according to the practical value of the reconstructed signal. The comparative experiment proves that the new detection method can get the detection result of the grounding current fault of the cable, which is more in line with the actual situation and has very high detection accuracy.

Walnut is one of the important economic tree species in the world. For the past few years, with the continuous expansion of walnut planting area, walnut bacterial blight caused by Xanthomonas campestrispv. juglandis has critically affected walnut production and caused economic losses. In this research, by comparing the gene sequences of X. campestrispv. juglandis and its closely related bacterial species, the 16S rDNA gene sequence was selected, and the specific primers were evaluated using PCR. Subsequently, the real-time fluorescence PCR specific detection method of X. campestrispv. juglandis was established and optimized. The specificity of real-time PCR was verified for 23 strains isolated from walnut and its surrounding soil, including eight target pathogens. The specific amplification was possible even when the cDNA template concentration was 7.0×10-5 µg/mL, hence, the detection sensitivity of the standard method is 7.0×10-5 µg/mL. The reliability of the established real-time PCR detection method in field detection was verified by the identification of target bacteria in 8 randomly collected healthy leaves and leaves of suspected walnut blight. This method laid a foundation for the early diagnosis of X. campestrispv. juglandis.

Privacy protection in video images is becoming one of the research focuses in the field of remote collaborative system. In this paper, a method for face detection, tracking and privacy protection is presented. According to skin-color distribution in the color space, we developed a statistical skin-color model through interactive sample training. Using this model we convert the color image to binary image and then segment face candidate region. Then we use a facial feature matching scheme for further detection. The presence or absence of a face in each region is verified by means of mouth detector. Real time detection and tracking can be achieved by using this method in video images. In order to speed up tracking, we improve the traditional method by adding motion prediction, which works better when several disturbing objects appear simultaneously. Finally we make the tracking region blurring and transmit the frames to the remote collaborative sites to obtain the privacy protection. The level of privacy protection can be dynamically adjusted according to collaborators' requests and credibility of remote sites. The experiment results show the proposed method not only has high speed and efficiency, but also is robust to head rotation to some extent.

The authors have developed a new method for real-time tumor tracking with dynamic multileaf-collimator (MLC) motion under condition of free breathing. Unlike other previously proposed tumor-tracking methods, their new method uses a preprogrammed dynamic MLC sequence in combination with real-time dose-rate control. This new scheme circumvents the technical challenge in MLC-based tumor tracking of having to control the MLC motion in real time, based on real-time detected tumor motion. With their new method, the movement of the tumor, as a function of breathing phase, amplitude, or tidal volume, is reflected in the preprogrammed MLC sequence. The irregularity of breathing during treatment is handled by real-time regulation of the machine dose rate, which effectively speeds up or slows down the delivery of radiation as needed. This method is based on the fact that all of the parameters in dynamic radiation delivery, including MLC motion, are enslaved to the cumulative dose, which, in turn, can be accelerated or decelerated by varying the dose rate. Because commercially available MLC systems do not allow the MLC delivery sequence to be modified in real time based on the patient's breathing signal, previously proposed tumor-tracking techniques using a MLC cannot be readily implemented in the clinic today. By using a preprogrammed MLC sequence to handle the required motion, the task for real-time control is greatly simplified. With their new scheme, which they call dose-rate-regulated tracking (DRRT), it is possible to use existing linear accelerators that have dynamic MLC capability to achieve real-time tumor tracking, provided that the beam dose rate can be controlled externally. Tracking-error evaluation for 13 patients out of 14 resulted in a tracking error of less than 1 mm (1 sigma), if the effect of the response time of the treatment machine on the dose-rate modulation can be neglected. Film measurements on a moving phantom with variable breathing patterns and DRRT delivery showed that 97% of the measurement points have gamma values less than 1 (for 3% and 2-mm criteria), while non-DRRT delivery showed only 87%. This study shows that real-time tracking is feasible with DRRT even when the patient breathing frequency is irregular. Effects of the variation of breathing amplitude and of base line drift on the tracking error with DRRT are discussed; pending further study, a criterion is suggested for patient selection in the application of this new technique in the clinic.

The combination of UAV camera and intelligent algorithm is a promising method for non-contact bridge crack detection. In this paper, an inspection tool based on UAV Image Acquisition Technology (UAVIAT) and Improved Intelligent Target Detection Technology (IITDT) called Improved Intelligent Real-Time Crack Detection Method for Bridges (IIRTCDMB) is proposed for efficient crack detection. The contributions of this paper are (1) The Squeeze-Excitement (SE) attention module is integrated into the target detection algorithm - You Only Look Once version 7 (YOLOv7) model to improve the learning ability of the feature channel. A Focal-efficient intersection over union (Focal-EIoU) loss function is also introduced to improve the regression accuracy of the model. As a result, a new crack image detection algorithm, YOLOv7-CD, is proposed. (2) A training process based on two-stage transfer learning (TSTL) is established, and hyper-parameter optimization of YOLOv7-CD is carried out. The feasibility and excellent performance of the proposed method are verified by applying it on the Cuntan Yangtze River Bridge. The results show that the average precision (AP) of the YOLOv7-CD model is improved by 3.19% compared with the original YOLOv7 model. After TSTL and hyperparameter optimization, the AP of the YOLOv7-CD model for bridge crack detection reaches 98.01%, which is higher than that of the popular target detection models. The IIRTCDMB proposed in this paper can acquire bridge surface images more safely and efficiently, and provide inspectors with more accurate structural crack information with lower computational and hardware requirements, which can provide technical support for the assessment of structural safety conditions and the formulation of maintenance programs.