Towards Raw Sensor Fusion in 3D Object Detection

Rövid, András; Remeli, Viktor

doi:10.1109/sami.2019.8782779

Cited by 10 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a recent study in 2019, Rövid et al went a step further to utilize the raw data and fuse it to realize the benefits early on in the cycle [30]. They fused camera image data with LiDAR pointclouds closest to the raw level of data extraction and its abstraction.…”

Section: Sensors and Their Input To Perceptionmentioning

confidence: 99%

“…Hence, the methodology to detect objects in the data from these sensors would be different as well. The research community has used this technique to detect objects in aerial, ground, and underwater environments [30][31][32][33][34]. 3.…”

Section: Sensors and Their Input To Perceptionmentioning

confidence: 99%

“…For successful navigation of an autonomous system, avoiding obstacles while in motion is an absolute requirement [30,32,33,35,170]. The vehicles must be able to navigate in their environment safely.…”

Section: Obstacle Avoidancementioning

confidence: 99%

See 2 more Smart Citations

Survey of Datafusion Techniques for Laser and Vision Based Sensor Integration for Autonomous Navigation

Kolar

Benavidez

Jamshidi

2020

Sensors

View full text Add to dashboard Cite

This paper focuses on data fusion, which is fundamental to one of the most important modules in any autonomous system: perception. Over the past decade, there has been a surge in the usage of smart/autonomous mobility systems. Such systems can be used in various areas of life like safe mobility for the disabled, senior citizens, and so on and are dependent on accurate sensor information in order to function optimally. This information may be from a single sensor or a suite of sensors with the same or different modalities. We review various types of sensors, their data, and the need for fusion of the data with each other to output the best data for the task at hand, which in this case is autonomous navigation. In order to obtain such accurate data, we need to have optimal technology to read the sensor data, process the data, eliminate or at least reduce the noise and then use the data for the required tasks. We present a survey of the current data processing techniques that implement data fusion using different sensors like LiDAR that use light scan technology, stereo/depth cameras, Red Green Blue monocular (RGB) and Time-of-flight (TOF) cameras that use optical technology and review the efficiency of using fused data from multiple sensors rather than a single sensor in autonomous navigation tasks like mapping, obstacle detection, and avoidance or localization. This survey will provide sensor information to researchers who intend to accomplish the task of motion control of a robot and detail the use of LiDAR and cameras to accomplish robot navigation.

show abstract

Section: Sensors and Their Input To Perceptionmentioning

confidence: 99%

Section: Sensors and Their Input To Perceptionmentioning

confidence: 99%

See 1 more Smart Citation

Survey of Datafusion Techniques for Laser and Vision Based Sensor Integration for Autonomous Navigation

Kolar

Benavidez

Jamshidi

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Authors in [14] focused on improving the detection of 3D objects using neural network architectures. The used data sets of images from sensors taken by autonomous driver.…”

Section: A 3d Object Detectionmentioning

confidence: 99%

“…As showing in Figure 2, the authors in [14] proposed a solution that fuses that LiDAR data with the camera data efficiently. Their approach is based on supplementing each 3D raw data with features acquired from the RGP image after processing these features via a 2D Object Detection CNN filter.…”

Section: A 3d Object Detectionmentioning

confidence: 99%

A Systematic Review on Fusion Techniques and Approaches Used in Applications

Jusoh

Almajali

2020

IEEE Access

View full text Add to dashboard Cite

Fusion technologies have rapidly evolved. These technologies are normally customized according to the needs of domains. Despite a large number of publications on intelligence fusion applications for various domains, they are scattered. The aim of this review is to present the state of the art for intelligence fusion applications within a specific domain. We identified three major domains for the purpose, namely robotics, military, and healthcare, during the initial process of the systematic review. These three domains are always in need of superior intelligence. Articles were searched mainly in IEEE Xplore. We limit the range of publications to the year 2014 to 2019, to focus on the most recent publications. We adopt the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) protocol to screen, filter and evaluate qualities of each retrieved article. As a result, we retrieved 675 articles at the initial stage of the search, we conducted screening and filtering process and reviewed 153 articles potential articles, and finally, we excluded 36 articles as they do not comply with our quality assessment criteria. Only 117 articles are included. The results of this study are a list of classified applications within the domains and a number of relevant techniques or approaches used in each classified application. The finding of this review showed that the most published works for the use of intelligence fusion are mainly applications in the robotics domain, where mostly used techniques are Kalman Filter and its variants. Outcomes of this study can be a guideline or an insight for researchers to further develop and implement in this field.

show abstract