Instantaneous Ghost Detection Identification in Automotive Scenarios

Prophet, Robert; Martínez, Javier; Michel, Juan-Carlos Fuentes; Ebelt, Randolf; Weber, Ingo; Vossiek, Martin

doi:10.1109/radar.2019.8835603

Cited by 34 publications

(12 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, we adopt this approach for our investigation. The authors of [3] present a detection algorithm suitable for the usage of a single measurement of one radar sensor. The algorithm is structured in three consecutive steps.…”

Section: Related Workmentioning

confidence: 99%

“…Instead of handcrafted features, the algorithm uses an occupancy grid map and a map of moving targets as input. The latter incorporates the concept of the first stage of the algorithm presented in [3]. Moreover, the random forest classifier is replaced by a convolutional neural network (CNN), which performs a segmentation of the input data.…”

Section: Related Workmentioning

confidence: 99%

“…This method needs two radar sensors and is limited to the detection of multi-path-related anomalies which cause ghost objects. In [3], a detection algorithm consisting of three consecutive steps using handcrafted features is presented in order to detect anomalies. The used dataset is limited to targets whose Doppler velocity is within the unambiguously measurable range.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Anomaly Detection in Radar Data Using PointNets

Griebel¹,

Authaler²,

Horn³

et al. 2021

Preprint

View full text Add to dashboard Cite

For autonomous driving, radar is an important sensor type. On the one hand, radar offers a direct measurement of the radial velocity of targets in the environment. On the other hand, in literature, radar sensors are known for their robustness against several kinds of adverse weather conditions. However, on the downside, radar is susceptible to ghost targets or clutter which can be caused by several different causes, e.g., reflective surfaces in the environment. Ghost targets, for instance, can result in erroneous object detections. To this end, it is desirable to identify anomalous targets as early as possible in radar data. In this work, we present an approach based on PointNets to detect anomalous radar targets. Modifying the PointNet-architecture driven by our task, we developed a novel grouping variant which contributes to a multi-form grouping module. Our method is evaluated on a real-world dataset in urban scenarios and shows promising results for the detection of anomalous radar targets.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Anomaly Detection in Radar Data Using PointNets

Griebel¹,

Authaler²,

Horn³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…On the side of machine learning, multiple relevant publications exist. In [3], several hand-crafted features are calculated for each moving detection and appended to the values measured by the sensor. The result is then fed to a classifier which tries to differentiate between nonclutter and two types of clutter detections.…”

Section: Related Workmentioning

confidence: 99%

Fast Rule-Based Clutter Detection in Automotive Radar Data

Kopp¹,

Kellner²,

Piroli³

et al. 2021

Preprint

View full text Add to dashboard Cite

Automotive radar sensors output a lot of unwanted clutter or ghost detections, whose position and velocity do not correspond to any real object in the sensor's field of view. This poses a substantial challenge for environment perception methods like object detection or tracking. Especially problematic are clutter detections that occur in groups or at similar locations in multiple consecutive measurements. In this paper, a new algorithm for identifying such erroneous detections is presented. It is mainly based on the modeling of specific commonly occurring wave propagation paths that lead to clutter. In particular, the three effects explicitly covered are reflections at the underbody of a car or truck, signals traveling back and forth between the vehicle on which the sensor is mounted and another object, and multipath propagation via specular reflection. The latter often occurs near guardrails, concrete walls or similar reflective surfaces. Each of these effects is described both theoretically and regarding a method for identifying the corresponding clutter detections. Identification is done by analyzing detections generated from a single sensor measurement only. The final algorithm is evaluated on recordings of real extra-urban traffic. For labeling, a semiautomatic process is employed. The results are promising, both in terms of performance and regarding the very low execution time. Typically, a large part of clutter is found, while only a small ratio of detections corresponding to real objects are falsely classified by the algorithm.

show abstract

“…In the latter, the ghost images are even used for a collision prevention system, highlighting the severity of mirror objects if they are undetected. A first attempt to remove multi-path using machine learning was done by [12]. They used handcrafted features with random forests and SVM variants on a small automotive data set.…”

Section: Related Workmentioning

confidence: 99%

Using Machine Learning to Detect Ghost Images in Automotive Radar

Kraus,

Scheiner,

Ritter

et al. 2020

Preprint

View full text Add to dashboard Cite

Radar sensors are an important part of driver assistance systems and intelligent vehicles due to their robustness against all kinds of adverse conditions, e.g., fog, snow, rain, or even direct sunlight. This robustness is achieved by a substantially larger wavelength compared to light-based sensors such as cameras or lidars. As a side effect, many surfaces act like mirrors at this wavelength, resulting in unwanted ghost detections. In this article, we present a novel approach to detect these ghost objects by applying data-driven machine learning algorithms. For this purpose, we use a large-scale automotive data set with annotated ghost objects. We show that we can use a state-of-the-art automotive radar classifier in order to detect ghost objects alongside real objects. Furthermore, we are able to reduce the amount of false positive detections caused by ghost images in some settings.

show abstract

Instantaneous Ghost Detection Identification in Automotive Scenarios

Cited by 34 publications

References 8 publications

Anomaly Detection in Radar Data Using PointNets

Anomaly Detection in Radar Data Using PointNets

Fast Rule-Based Clutter Detection in Automotive Radar Data

Using Machine Learning to Detect Ghost Images in Automotive Radar

Contact Info

Product

Resources

About