Target Reconstruction of Streak Tube Imaging Lidar Based on Gaussian Fitting

Qing-yu, 袁清钰 Yuan; Lihong, 牛丽红 Niu; Cui-chun, 胡翠春 Hu; Lei, 吴磊 Wu; Hongru, 杨鸿儒 Yang; Bing, 俞兵 Yu

doi:10.3788/gzxb20174612.1211002

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method returns continuous values and allows one to obtain pulse widths with many significant digits (it even corrects to the first six decimal places). Such high resolution is far too high for actual LiDAR applications, where the general ranging resolution is within the range of 5–30 cm [ 22 , 23 , 24 , 25 , 26 ], and consequently pursuing results with such high resolution is meaningless.…”

Section: Discussionmentioning

confidence: 99%

“…There are two approaches to this problem: one is using a regression network [1 which involves regressing the input waveform to obtain a regression mode minimizes the average error in predicting the pulse width of the input waveform method returns continuous values and allows one to obtain pulse widths with significant digits (it even corrects to the first six decimal places). Such high resolu far too high for actual LiDAR applications, where the general ranging resolution is the range of 5-30 cm [22][23][24][25][26], and consequently pursuing results with such high reso is meaningless.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Neural Network-Based Phase-Modulated Continuous-Wave LiDAR

Zhang,

Wang,

Zhang

et al. 2024

Sensors

View full text Add to dashboard Cite

LiDAR has high accuracy and resolution and is widely used in various fields. In particular, phase-modulated continuous-wave (PhMCW) LiDAR has merits such as low power, high precision, and no need for laser frequency modulation. However, with decreasing signal-to-noise ratio (SNR), the noise on the signal waveform becomes so severe that the current methods to extract the time-of-flight are no longer feasible. In this paper, a novel method that uses deep neural networks to measure the pulse width is proposed. The effects of distance resolution and SNR on the performance are explored. Recognition accuracy reaches 81.4% at a 0.1 m distance resolution and the SNR is as low as 2. We simulate a scene that contains a vehicle, a tree, a house, and a background located up to 6 m away. The reconstructed point cloud has good fidelity, the object contours are clear, and the features are restored. More precisely, the three distances are 4.73 cm, 6.00 cm, and 7.19 cm, respectively, showing that the performance of the proposed method is excellent. To the best of our knowledge, this is the first work that employs a neural network to directly process LiDAR signals and to extract their time-of-flight.

show abstract