Enhanced Iron-Tunnel Recognition for Automotive Radars

Lee, Jae-Eun; Lim, Hae-Seung; Jeong, Seonghee; Kim, Seong-Cheol; Shin, Hyun-Chool

doi:10.1109/tvt.2015.2460992

Cited by 24 publications

(33 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The higher the false alarm rate, the higher the probability that the target is undetected, and the lower the false alarm rate, the higher the probability of false detection. Therefore, it is necessary to set a false alarm rate suitable for the road environment, as suggested in [15]. The red circles are the targets driving ahead, and the target is detected properly when the magnitude of the point in the circle is greater than the CFAR threshold.…”

Section: B Target Detection In Diverse Road Structuresmentioning

confidence: 99%

“…However, these studies [12]- [14] have a disadvantage, that is, they can be applied only to a specific road environment. In [15], they proposed a technique for recognizing iron tunnels using entropy of received signal amplitude. However, in [15], the road environment was recognized only for periodic iron structures.…”

Section: Introductionmentioning

confidence: 99%

“…In [15], they proposed a technique for recognizing iron tunnels using entropy of received signal amplitude. However, in [15], the road environment was recognized only for periodic iron structures. In addition, the statistical characteristics of the received signal according to the road environment were extracted and classified using a support vector machine (SVM) in [16].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Road Environment Recognition for Automotive FMCW RADAR Systems Through Convolutional Neural Network

Sim

Lee

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

In this study, we propose a method to recognize road environments with automotive frequency-modulated continuous wave (FMCW) radar systems. For automotive radar systems on the road, diverse road environments are observed. Each road environment generates unnecessary echoes known as clutter, and the magnitude distribution of received radar signal varies depending on road structures. Therefore, it is necessary to classify the road environment and adopt a target detection algorithm suitable for each road environment characteristic. To recognize the road environment in advance, it is necessary to identify the section where the road environment changes. In this paper, we define a changed road area as a transition region, and we classify the road environment and transition regions to improve the road environment recognition performance. Road environments are recognized by applying convolutional neural networks to the frequency-domain received signals of 77 GHz FMCW automotive radar systems. Experimental results in real-road environments demonstrate that the proposed method achieves 100% recognition performance, which is better if compared with that of the conventional methods. INDEX TERMS Automotive frequency-modulated continuous wave (FMCW) radar, road environment recognition, convolutional neural network.

show abstract

Section: B Target Detection In Diverse Road Structuresmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Road Environment Recognition for Automotive FMCW RADAR Systems Through Convolutional Neural Network

Sim

Lee

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently, studies have been conducted in the time-frequency domain, instead of the frequency domain. There has been research on the recognition of iron tunnels by measuring the degree of spectral spreading through the analysis of the spectrum characteristics of the received radar signal in iron tunnel [14], and harmonic clutter suppression by measuring the periodicity of harmonic clutters using spectrum [15], [16]. In this paper, for supporting the construction of the road map containing various objects, we focus on stationary and moving object classification.…”

Section: Introductionmentioning

confidence: 99%

Classification and Spectral Mapping of Stationary and Moving Objects in Road Environments Using FMCW Radar

Song

Shin

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

In order to establish a reliable map of the road environment, this paper aims to classify the stationary and moving objects unlike the previous researches which generally focus on object recognition. The characteristics of the radar signals of stationary and moving objects were analyzed and the relation between the slope of pattern in radar time-frequency spectrum and relative velocity of the object was described mathematically. To discriminate the stationary and moving objects, the difference between the measured velocity by the slope and the velocity of the ego-vehicle was proposed as a feature. The statistical characteristics of stationary and moving objects according to the proposed feature were modeled using Gaussian model. To investigate the performance of the proposed method, the similarity between modeling of stationary and moving objects was quantified. Additionally, the receiver operating characteristics (ROC) curve and the correlation coefficient between the proposed feature and the ground-truth feature map was applied to verify the performance. INDEX TERMS Automotive radar, radar signal processing, road environment map, FMCW radar, object classification.

show abstract

“…Automotive radars have attracted great attention due to their safety precautions [1,2,3,4]. Nowadays, the 77 GHz radars represent the development trend of future automotive radars [5,6,7,8].…”

Section: Introductionmentioning

confidence: 99%

Hybrid antenna arrays with high angular resolution for 77 GHz automotive radars

Jiafei

Zou

Jiang

et al. 2020

IEICE Electron. Express

View full text Add to dashboard Cite

An antenna array system with high angular resolution is proposed to adapt the demands of both medium-range radar (MRR) and longrange radar (LRR) detections for 77 GHz automotive radars. Both the MRR and LRR modes are integrated into one substrate based on the optimized sparse array topology, which makes full use of the antenna aperture size to improve the angular resolution of the proposed system. Two-dimensional series-fed weighting arrays are designed via the Taylor synthesis method to effectively heighten the antenna gain and restrain the sidelobe level. After completing the fabrication, measurement results of the proposed antenna array are in good agreement with the simulation results. Moreover, the angular resolution is verified to be 0.5°by adopting the coherent signal space method (CSM) with stepped frequency transmitting waveform, which validates the effectiveness of the proposal.

show abstract

Enhanced Iron-Tunnel Recognition for Automotive Radars

Cited by 24 publications

References 14 publications

Road Environment Recognition for Automotive FMCW RADAR Systems Through Convolutional Neural Network

Road Environment Recognition for Automotive FMCW RADAR Systems Through Convolutional Neural Network

Classification and Spectral Mapping of Stationary and Moving Objects in Road Environments Using FMCW Radar

Hybrid antenna arrays with high angular resolution for 77 GHz automotive radars

Contact Info

Product

Resources

About