Particle filter‐based vehicle tracking via HOG features after image stabilisation in intelligent drive system

Kong, Xiaofang; Chen, Qian; Gu, Guohua; Ren, Kan; Qian, Wei; Liu, Zewei

doi:10.1049/iet-its.2018.5334

Cited by 9 publications

(6 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The clustering centers and membership degrees have been regularly changed during the iterations [61]. A finite collection of N elements Q = 𝑞 , 𝑞 , ..., 𝑞 is In the next step, Gamma correction [49,50] is used to alter the denoised image's intensity since the region of interest can be detected most effectively when the brightness is high [51]. The power-law for gamma correction is given as:…”

Section: Fuzzy C-mean Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Vehicle Detection and Classification via YOLOv8 and Deep Belief Network over Aerial Image Sequences

Al Mudawi,

Qureshi,

Abdelhaq

et al. 2023

Sustainability

View full text Add to dashboard Cite

Vehicle detection and classification are the most significant and challenging activities of an intelligent traffic monitoring system. Traditional methods are highly computationally expensive and also impose restrictions when the mode of data collection changes. This research proposes a new approach for vehicle detection and classification over aerial image sequences. The proposed model consists of five stages. All of the images are preprocessed in the first stage to reduce noise and raise the brightness level. The foreground items are then extracted from these images using segmentation. The segmented images are then passed onto the YOLOv8 algorithm to detect and locate vehicles in each image. The feature extraction phase is then applied to the detected vehicles. The extracted feature involves Scale Invariant Feature Transform (SIFT), Oriented FAST and Rotated BRIEF (ORB), and KAZE features. For classification, we used the Deep Belief Network (DBN) classifier. Based on classification, the experimental results across the three datasets produced better outcomes; the proposed model attained an accuracy of 95.6% over Vehicle Detection in Aerial Imagery (VEDAI) and 94.6% over Vehicle Aerial Imagery from a Drone (VAID) dataset, respectively. To compare our model with the other standard techniques, we have also drawn a comparative analysis with the latest techniques in the research.

show abstract

Section: Fuzzy C-mean Segmentationmentioning

confidence: 99%

“…The gammacorrected images are given in Figure 3. In the next step, Gamma correction [49,50] is used to alter the denoised image's intensity since the region of interest can be detected most effectively when the brightness is high [51]. The power-law for gamma correction is given as:…”

Section: Fuzzy C-mean Segmentationmentioning

confidence: 99%

Vehicle Detection and Classification via YOLOv8 and Deep Belief Network over Aerial Image Sequences

Al Mudawi,

Qureshi,

Abdelhaq

et al. 2023

Sustainability

View full text Add to dashboard Cite

show abstract

“…With the optical flow that represents motion features directly, we demonstrate that the temporal module is not necessary for our system. On the other hand, traditional features for temporal tracking such as HOG and HOF are 2D in nature, and the tracking performance depends heavily on whether distinctive feature points are available [37]. Our optical flow is calculated by first projecting the 3D point cloud from the depth image with the camera egomotion, and then mapping the angle and magnitude of the per-pixel 3D motion into the 2D color space, as shown in Fig.…”

Section: Optical Flow Calculationmentioning

confidence: 99%

Multi‐task deep learning with optical flow features for self‐driving cars

Shum

2020

IET intell. transp. syst

View full text Add to dashboard Cite

The control of self-driving cars has received growing attention recently. While existing research shows promising results in vehicle control using video from a monocular dash camera, there has been very limited work on directly learning vehicle control from motion-based cues. Such cues are powerful features for visual representations, as they encode the per-pixel movement between two consecutive images, allowing a system to effectively map the features into the control signal. We propose a new framework that exploits the use of a motion-based feature known as optical flow extracted from the dash camera, and demonstrates that such a feature is effective in significantly improving the accuracy of the control signals. Our proposed framework involves two main components. The flow predictor, as a self-supervised deep network, models the underlying scene structure from consecutive frames and generates the optical flow. The controller, as a supervised multi-task deep network, predicts both steer angle and speed. We demonstrate that the proposed framework using the optical flow features can effectively predict control signals from a dash camera video. Using the Cityscapes dataset, we validate that the system prediction has errors as low as 0.0130 rad/s on steer angle and 0.0615 m/s on speed, outperforming existing research.

show abstract

“…Nevertheless, its computational speed and accuracy could not be optimal in case of the elaborate environments. In [23]- [25], Particle filter-based vehicle tracking via HOG features is very robust when fast-moving human target but this algorithm is hard to integrate with a mobile system. In [26] and [27], the Camshift algorithm is well-known as popular tracking human method.…”

Section: Introductionmentioning

confidence: 99%

Real-time Target Human Tracking using Camshift and LucasKanade Optical Flow Algorithm

Nguyen¹,

Nguyen²,

Bui³

et al. 2021

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

In this paper, a novel is proposed for real-time tracking human targets in cases of high influence from complexity environment with a normal camera. Firstly, based on Oriented FAST and Rotated BRIEF features, the Lucas-Kanade Optical Flow algorithm is used to track reliable keypoints. This method represents a valuable performance to decline the effect of the illumination or displacement of human targets. Secondly, the area of the human target in the frame is determined more precise by using the Camshift algorithm. Compared to the existing approaches, the proposed method has some merits to some extents including rapid calculations in implementation, high accuracy in case of similar objects detection, the ability to deploy easily on mobile devices. Finally, the effectiveness of the proposed tracking algorithm is demonstrated via experimental results.

show abstract

Particle filter‐based vehicle tracking via HOG features after image stabilisation in intelligent drive system

Cited by 9 publications

References 42 publications

Vehicle Detection and Classification via YOLOv8 and Deep Belief Network over Aerial Image Sequences

Vehicle Detection and Classification via YOLOv8 and Deep Belief Network over Aerial Image Sequences

Multi‐task deep learning with optical flow features for self‐driving cars

Real-time Target Human Tracking using Camshift and LucasKanade Optical Flow Algorithm

Contact Info

Product

Resources

About