Visualisation Functions in Advanced Camera-Based Surround View Systems

Friebe, Markus; Petzold, Johannes

doi:10.1007/978-3-319-08087-1_24

Cited by 3 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A hidden layer consisting of LSTM cells (networks with 20, 70, 100, and 150 memory elements in the hidden layer are analyzed), a fully connected layer, and an output layer fully connected with the last hidden layer (regression layer on which predicted displacement-output of the network, are obtained ( 17)). The input layer consists of 11 features (11), which are normalized using min-max normalization (see Section 4.1)-vector V is obtained ( 16): V = ∆x , ∆y , a x , a y , a z , g x , g y , g z , m x , m y , m z (16) where ∆x -normalized displacement in the X-axis; ∆y -normalized displacement in the Y-axis; a x , a y , a z -normalized acceleration from the accelerometer, respectively, in the X, Y, and Z-axes; g x , g y , g z -normalized angular velocity from the gyroscope, respectively, in the X, Y, and Z-axes; and m x , m y , m z -normalized magnetic field from the magnetometer, respectively, in the X, Y, and Z-axes.…”

Section: Network Structurementioning

confidence: 99%

“…Many technologies provide additional information to drivers, allowing them to see things normally invisible to the driver, such as a vehicle in the blind spot. Radars, lidars [9][10][11][12][13][14], video analysis [15][16][17][18][19][20], ultrasonic and hall systems [21,22] observe and scan 2 of 21 the vehicle's surroundings and can provide information about the impending danger (i.e., the position of the object relative to an obstacle or another traffic participant is determined). They can also decide and act without the driver's intervention, e.g., brake in an emergency or park the vehicle in the indicated place (active parking assist) [23].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Using the LSTM Neural Network and the UWB Positioning System to Predict the Position of Low and High Speed Moving Objects

Paszek,

Grzechca

2023

Sensors

View full text Add to dashboard Cite

Automation of transportation will play a crucial role in the future when people driving vehicles will be replaced by autonomous systems. Currently, the positioning systems are not used alone but are combined in order to create cooperative positioning systems. The ultra-wideband (UWB) system is an excellent alternative to the global positioning system (GPS) in a limited area but has some drawbacks. Despite many advantages of various object positioning systems, none is free from the problem of object displacement during measurement (data acquisition), which affects positioning accuracy. In addition, temporarily missing data from the absolute positioning system can lead to dangerous situations. Moreover, data pre-processing is unavoidable and takes some time, affecting additionally the object’s displacement in relation to its previous position and its starting point of the new positioning process. So, the prediction of the position of an object is necessary to minimize the time when the position is unknown or out of date, especially when the object is moving at high speed and the position update rate is low. This article proposes using the long short-term memory (LSTM) artificial neural network to predict objects’ positions based on historical data from the UWB system and inertial navigation. The proposed solution creates a reliable positioning system that predicts 10 positions of low and high-speed moving objects with an error below 10 cm. Position prediction allows detection of possible collisions—the intersection of the trajectories of moving objects.

show abstract

Section: Network Structurementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Using the LSTM Neural Network and the UWB Positioning System to Predict the Position of Low and High Speed Moving Objects

Paszek,

Grzechca

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The UWB system, apart from the option of data transmission, allows for determining the position with high accuracy, which together with the growing interest in autonomous vehicles will be important in the smart cities or smart industries [ 13 , 14 , 15 ]. Positioning systems such as Lidar, radar, ultrasound, interaction sensors, or cameras provide information about the vehicle’s surroundings [ 16 , 17 , 18 , 19 , 20 ]. Their advantage lies in independence from infrastructure.…”

Section: Introductionmentioning

confidence: 99%

Design of the UWB Positioning System Simulator for LOS/NLOS Environments

Paszek

Grzechca

Becker

2021

Sensors

View full text Add to dashboard Cite

UWB is a rapidly developing technology characterised by high positioning accuracy, additional data transferability, and communication security. Low costs and energy demand makes it a system that meets the requirements of smart cities (e.g., smart mobility). The analysis of the positioning accuracy of moving objects requires a ground truth. For the UWB system, it should have an accuracy of the order of millimetres. The generated data can be used to minimize the cost and time needed to perform field tests. However, there is no UWB simulators which can consider the variable characteristics of operation along with distance to reflect the operation of real systems. This article presents a 2D UWB simulator for outdoor open-air areas with obstacles and a method of analysing data from the real UWB system under line-of-sight (LOS) and non-line-of-sight conditions. Data are recorded at predefined outdoor reference distances, and by fitting normal distributions to this data and modelling the impact of position changes the real UWB system can be simulated and it makes it possible to create virtual measurements for other locations. Furthermore, the presented method of describing the path using time-dependent equations and obstacles using a set of inequalities allows for reconstructing the real test scenario with moving tags with high accuracy.

show abstract

Vehicle-mounted surround vision algorithm based on heterogeneous architecture

Liu

Zhang

et al. 2020

Multimed Tools Appl

View full text Add to dashboard Cite

Visualisation Functions in Advanced Camera-Based Surround View Systems

Cited by 3 publications

References 3 publications

Using the LSTM Neural Network and the UWB Positioning System to Predict the Position of Low and High Speed Moving Objects

Using the LSTM Neural Network and the UWB Positioning System to Predict the Position of Low and High Speed Moving Objects

Design of the UWB Positioning System Simulator for LOS/NLOS Environments

Vehicle-mounted surround vision algorithm based on heterogeneous architecture

Contact Info

Product

Resources

About