Target Fusion Detection of LiDAR and Camera Based on the Improved YOLO Algorithm

Han, Jian; Liao, Yaping Joyce; Zhang, Junyou; Wang, Shufeng; Li, Sixian

doi:10.3390/math6100213

Cited by 39 publications

(25 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An imputed detection can therefore be simulated using the sensor model and the expected position of the tracked object. At the moment of missing detection, we can let the sensor mode evolution model Equation (22) choose the most likely course of evolution of c t . It is safe to assume that the missing detection PDF is the same as that of the observed data, p Y|X,C y t x…”

Section: Handling Missing Detectionsmentioning

confidence: 99%

“…The goal is to analyze the convergence of the switching observation model particle filter explained by the set of equations in Equation (22). To that end, the object x starts moving perpendicular to the ego vehicle starting from ρ 0 = 20 m, θ 0 = −60 • with initial velocity magnitude of 1.38 ms −1 and velocity orientation of θ = 90 • .…”

Section: Switching Observation Modelmentioning

confidence: 99%

See 1 more Smart Citation

Cooperative Multi-Sensor Tracking of Vulnerable Road Users in the Presence of Missing Detections

Dimitrievski

Hamme

Veelaert

et al. 2020

Sensors

View full text Add to dashboard Cite

This paper presents a vulnerable road user (VRU) tracking algorithm capable of handling noisy and missing detections from heterogeneous sensors. We propose a cooperative fusion algorithm for matching and reinforcing of radar and camera detections using their proximity and positional uncertainty. The belief in the existence and position of objects is then maximized by temporal integration of fused detections by a multi-object tracker. By switching between observation models, the tracker adapts to the detection noise characteristics making it robust to individual sensor failures. The main novelty of this paper is an improved imputation sampling function for updating the state when detections are missing. The proposed function uses a likelihood without association that is conditioned on the sensor information instead of the sensor model. The benefits of the proposed solution are two-fold: firstly, particle updates become computationally tractable and secondly, the problem of imputing samples from a state which is predicted without an associated detection is bypassed. Experimental evaluation shows a significant improvement in both detection and tracking performance over multiple control algorithms. In low light situations, the cooperative fusion outperforms intermediate fusion by as much as 30%, while increases in tracking performance are most significant in complex traffic scenes.

show abstract

Section: Handling Missing Detectionsmentioning

confidence: 99%

Section: Switching Observation Modelmentioning

confidence: 99%

Cooperative Multi-Sensor Tracking of Vulnerable Road Users in the Presence of Missing Detections

Dimitrievski

Hamme

Veelaert

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Motor vehicles are increasing dramatically with the rapid economic development [1,2]. However, the power used by the internal combustion engine for power output generally accounts for only 30%-45% (diesel) or 20%-30% (gasoline) of the total fuel combustion heat.…”

Section: Introductionmentioning

confidence: 99%

Performance Study on Methanol Steam Reforming Rib Micro-Reactor with Waste Heat Recovery

Wang

Chen

2020

Energies

View full text Add to dashboard Cite

Automobile exhaust heat recovery is considered to be an effective means to enhance fuel utilization. The catalytic production of hydrogen by methanol steam reforming is an attractive option for onboard mobile applications, due to its many advantages. However, the reformers of conventional packed bed type suffer from axial temperature gradients and cold spots resulting from severe limitations of mass and heat transfer. These disadvantages limit reformers to a low efficiency of catalyst utilization. A novel rib microreactor was designed for the hydrogen production from methanol steam reforming heated by automobile exhaust, and the effect of inlet exhaust and methanol steam on reactor performance was numerically analyzed in detail, with computational fluid dynamics. The results showed that the best operating parameters were the counter flow, water-to-alcohol (W/A) of 1.3, exhaust inlet velocity of 1.1 m/s, and exhaust inlet temperature of 773 K, when the inlet velocity and inlet temperature of the reactant were 0.1 m/s and 493 K, respectively. At this condition, a methanol conversion of 99.4% and thermal efficiency of 28% were achieved, together with a hydrogen content of 69.6%.

show abstract

“…The detection of preceding vehicles plays a decisive role in realizing rational planning of the driving path, maintaining the correct distance, and ensuring driving safety for autonomous vehicles [3,4]. Recently, preceding vehicle detection has become a research hotspot due to its necessity for autonomous vehicles, and many detection algorithms have been proposed [5][6][7][8].…”

Section: Introductionmentioning

confidence: 99%

“…Method of selecting vehicle sizes. Weighted mean value of cluster centroids 1 and 2 is obtained by Equation(7).…”

mentioning

confidence: 99%

Preceding Vehicle Detection Using Faster R-CNN Based on Speed Classification Random Anchor and Q-Square Penalty Coefficient

Cui

Wang

et al. 2019

Electronics

View full text Add to dashboard Cite

At present, preceding vehicle detection remains a challenging problem for autonomous vehicle technologies. In recent years, deep learning has been shown to be successful for vehicle detection, such as the faster region with a convolutional neural network (Faster R-CNN). However, when the host vehicle speed increases or there is an occlusion in front, the performance of the Faster R-CNN algorithm usually degrades. To obtain better performance on preceding vehicle detection when the speed of the host vehicle changes, a speed classification random anchor (SCRA) method is proposed. The reasons for degraded detection accuracy when the host vehicle speed increases are analyzed, and the factor of vehicle speed is introduced to redesign the anchors. Redesigned anchors can adapt to changes of the preceding vehicle size rule when the host vehicle speed increases. Furthermore, to achieve better performance on occluded vehicles, a Q-square penalty coefficient (Q-SPC) method is proposed to optimize the Faster R-CNN algorithm. The experimental validation results show that compared with the Faster R-CNN algorithm, the SCRA and Q-SPC methods have certain significance for improving preceding vehicle detection accuracy.

show abstract

Target Fusion Detection of LiDAR and Camera Based on the Improved YOLO Algorithm

Cited by 39 publications

References 13 publications

Cooperative Multi-Sensor Tracking of Vulnerable Road Users in the Presence of Missing Detections

Cooperative Multi-Sensor Tracking of Vulnerable Road Users in the Presence of Missing Detections

Performance Study on Methanol Steam Reforming Rib Micro-Reactor with Waste Heat Recovery

Preceding Vehicle Detection Using Faster R-CNN Based on Speed Classification Random Anchor and Q-Square Penalty Coefficient

Contact Info

Product

Resources

About