Improved Human Detection with a Fusion of Laser Scanner and Vision/Infrared Information for Mobile Applications

Budzan, Sebastian; Wyżgolik, R.; Ilewicz, Witold

doi:10.3390/app8101967

Cited by 8 publications

(5 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Monitoring movement during and after the aircraft landing phase is another application that can be done with laser scanners, allowing the improvement of airport safety thanks to knowledge of accurate position and speed (accuracy of 17 cm and 0.17 m/s, respectively) [9]. Also, human detection and monitoring takes advantage from laser scanning information, together with infrared imagery, leveraging the two technologies to complement one another [14]. A particular application of movement detection is shown in [12], where the vibration of fan blades was monitored through a laser scanner vibrometry (LSV) technology, providing the means for determining harmonics.…”

Section: Featured Papersmentioning

confidence: 99%

“…Laser scanning applications covered in this special issue can be divided into the following categories: multi-wavelength LiDAR [3,4], mobile mapping support for indoor [5][6][7], outdoor, and other applications [8], object tracking and navigation [9][10][11], deformation monitoring [12,13], modelling and detection [14][15][16], geometric accuracy assessment [17][18][19], and hybrid technologies like LiDARgrammetry [20], which are summarized in more detail in the following section.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Preface of Special Issue on Laser Scanning

2019

View full text Add to dashboard Cite

show abstract

Section: Featured Papersmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Preface of Special Issue on Laser Scanning

2019

View full text Add to dashboard Cite

show abstract

“…The FxLMS applied to vehicles, in many cases, also takes advantage of a so-called preview signal, i.e., additional information available in advance about road unevenness or road obstacles located in front of the vehicle. Such information can be provided by different sensors, e.g., a single laser scanner or an algorithm of sensor fusion dedicated to mobile applications [ 34 ].…”

Section: Introductionmentioning

confidence: 99%

Identification of Control-Related Signal Path for Semi-Active Vehicle Suspension with Magnetorheological Dampers

Krauze

2023

Sensors

View full text Add to dashboard Cite

This paper presents a method for the identification of control-related signal paths dedicated to a semi-active suspension with MR (magnetorheological) dampers, which are installed in place of standard shock absorbers. The main challenge comes from the fact that the semi-active suspension needs to be simultaneously subjected to road-induced excitation and electric currents supplied to the suspension MR dampers, while a response signal needs to be decomposed into road-related and control-related components. During experiments, the front wheels of an all-terrain vehicle were subjected to sinusoidal vibration excitation at a frequency equal to 12 Hz using a dedicated diagnostic station and specialised mechanical exciters. The harmonic type of road-related excitation allowed for its straightforward filtering from identification signals. Additionally, front suspension MR dampers were controlled using a wideband random signal with a 25 Hz bandwidth, different realisations, and several configurations, which differed in the average values and deviations of control currents. The simultaneous control of the right and left suspension MR dampers made it necessary to decompose the vehicle vibration response, i.e., the front vehicle body acceleration signal, into components related to the forces generated by different MR dampers. Measurement signals used for identification were taken from numerous sensors available in the vehicle, e.g., accelerometers, suspension force and deflection sensors, and sensors of electric currents, which control the instantaneous damping parameters of MR dampers. The final identification was carried out for control-related models evaluated in the frequency domain and revealed several resonances of the vehicle response and their dependence on the configurations of control currents. In addition, the parameters of the vehicle model with MR dampers and the diagnostic station were estimated based on the identification results. The analysis of the simulation results of the implemented vehicle model carried out in the frequency domain showed the influence of the vehicle load on the absolute values and phase shifts of control-related signal paths. The potential future application of the identified models lies in the synthesis and implementation of adaptive suspension control algorithms such as FxLMS (filtered-x least mean square). Adaptive vehicle suspensions are especially preferred for their ability to quickly adapt to varying road conditions and vehicle parameters.

show abstract

“…With the development of hardware technology, the fusion of multiple sensors and multiple algorithms was used for UGV (unmanned ground vehicle) [19][20][21]. To overcome the low accuracy and poor robustness of a single detection method, a novel algorithm was proposed that combines an SVM (Support Vector Machine) and a K-nearest neighbors algorithm and the confidence map under a Bayesian framework [22].…”

Section: Introductionmentioning

confidence: 99%

Detection and Modeling of Unstructured Roads in Forest Areas Based on Visual-2D Lidar Data Fusion

Lei

Yao

Zhao

et al. 2021

Forests

View full text Add to dashboard Cite

The detection and recognition of unstructured roads in forest environments are critical for smart forestry technology. Forest roads lack effective reference objects and manual signs and have high degrees of nonlinearity and uncertainty, which pose severe challenges to forest engineering vehicles. This research aims to improve the automation and intelligence of forestry engineering and proposes an unstructured road detection and recognition method based on a combination of image processing and 2D lidar detection. This method uses the “improved SEEDS + Support Vector Machine (SVM)” strategy to quickly classify and recognize the road area in the image. Combined with the remapping of 2D lidar point cloud data on the image, the actual navigation requirements of forest unmanned navigation vehicles were fully considered, and road model construction based on the vehicle coordinate system was achieved. The algorithm was transplanted to a self-built intelligent navigation platform to verify its feasibility and effectiveness. The experimental results show that under low-speed conditions, the system can meet the real-time requirements of processing data at an average of 10 frames/s. For the centerline of the road model, the matching error between the image and lidar is no more than 0.119 m. The algorithm can provide effective support for the identification of unstructured roads in forest areas. This technology has important application value for forestry engineering vehicles in autonomous inspection and spraying, nursery stock harvesting, skidding, and transportation.

show abstract

Improved Human Detection with a Fusion of Laser Scanner and Vision/Infrared Information for Mobile Applications

Cited by 8 publications

References 49 publications

Preface of Special Issue on Laser Scanning

Preface of Special Issue on Laser Scanning

Identification of Control-Related Signal Path for Semi-Active Vehicle Suspension with Magnetorheological Dampers

Detection and Modeling of Unstructured Roads in Forest Areas Based on Visual-2D Lidar Data Fusion

Contact Info

Product

Resources

About