A Boosted Multi-Task Model for Pedestrian Detection With Occlusion Handling

Zhu, Chao; Peng, Yuxin

doi:10.1109/tip.2015.2483376

Cited by 31 publications

(7 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nonetheless, if j k is large, which will lead to the loss of weak details. The recommended range of j k is [4,6] when the noise variance of the hazy image is less than 2, other recommended ranges are [2,4]. The details of these parameters are not repeated here.…”

Section: Parameter Analysis and Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Image Haze Removal Algorithm Based on Nonsubsampled Contourlet Transform

2021

View full text Add to dashboard Cite

In order to avoid the noise diffusion and amplification caused by traditional dehazing algorithms, a single image haze removal algorithm based on nonsubsampled contourlet transform (HRNSCT) is proposed. The HRNSCT removes haze only from the low-frequency components and suppresses noise in the high-frequency components of hazy images, preventing noise amplification caused by traditional dehazing algorithms. First, the nonsubsampled contourlet transform (NSCT) is used to decompose each channel of a hazy and noisy color image into low-frequency sub-band and high-frequency direction sub-bands. Second, according to the low-frequency sub-bands of the three channels, the color attenuation prior and dark channel prior are combined to estimate the transmission map, and use the transmission map to dehaze the low frequency sub-bands. Then, to achieve the noise suppression and details enhancement of the dehazed image, the high-frequency direction sub-bands of the three channels are shrunk, and those shrunk sub-bands are enhanced according to the transmission map. Finally, the nonsubsampled contourlet inverse transform is performed on the dehazed low-frequency sub-bands and enhanced high-frequency sub-bands to reconstruct the dehazed and noise-suppressed image. The experimental results show that the HRNSCT provides excellent haze removal and noise suppression performance and prevents noise amplification during dehazing, making it well suited for removing haze from noisy images.

show abstract

Section: Parameter Analysis and Discussionmentioning

confidence: 99%

“…Most existing dehazing algorithms are based on image enhancement [2], [3], physical models [4], [5], [6] or machine learning [7], [8]. These algorithms can be divided into two categories, namely those with and without noise suppression.…”

Section: Introductionmentioning

confidence: 99%

Image Haze Removal Algorithm Based on Nonsubsampled Contourlet Transform

2021

View full text Add to dashboard Cite

show abstract

“…In adverse conditions like low illumination, night, snowfall, and rain, it is further difficult to detect the dynamic entities while work has been done in this regards by using thermal images [ 171 ]. In both indoor and outdoor environments, occlusion is another big hindrance with dynamic entity detection and solutions have been proposed [ 172 , 173 ], although it still is an open problem. Fusing trajectory smoothing into SLAM process : SLAM in an indispensable module for any mobile robot.…”

Section: Challengesmentioning

confidence: 99%

Path Smoothing Techniques in Robot Navigation: State-of-the-Art, Current and Future Challenges

Ravankar

Kobayashi

et al. 2018

Sensors

235

110

View full text Add to dashboard Cite

Robot navigation is an indispensable component of any mobile service robot. Many path planning algorithms generate a path which has many sharp or angular turns. Such paths are not fit for mobile robot as it has to slow down at these sharp turns. These robots could be carrying delicate, dangerous, or precious items and executing these sharp turns may not be feasible kinematically. On the contrary, smooth trajectories are often desired for robot motion and must be generated while considering the static and dynamic obstacles and other constraints like feasible curvature, robot and lane dimensions, and speed. The aim of this paper is to succinctly summarize and review the path smoothing techniques in robot navigation and discuss the challenges and future trends. Both autonomous mobile robots and autonomous vehicles (outdoor robots or self-driving cars) are discussed. The state-of-the-art algorithms are broadly classified into different categories and each approach is introduced briefly with necessary background, merits, and drawbacks. Finally, the paper discusses the current and future challenges in optimal trajectory generation and smoothing research.

show abstract

“…However its limitation is that the shallow feature is not powerful enough in complicated traffic scenes. For pedestrian detection with occlusion under complex scene, a boosted multi-task detector is proposed in [20] to handle the occlusion problem effectively.…”

Section: Related Workmentioning

confidence: 99%

VSSA-NET: Vertical Spatial Sequence Attention Network for Traffic Sign Detection

Yuan

Xiong

Wang

2019

IEEE Trans. on Image Process.

161

View full text Add to dashboard Cite

Although traffic sign detection has been studied for years and great progress has been made with the rise of deep learning technique, there are still many problems remaining to be addressed. For complicated real-world traffic scenes, there are two main challenges. Firstly, traffic signs are usually smallsize objects, which makes it more difficult to detect than large ones; Secondly, it is hard to distinguish false targets which resemble real traffic signs in complex street scenes without context information. To handle these problems, we propose a novel end-to-end deep learning method for traffic sign detection in complex environments. Our contributions are as follows: 1) We propose a multi-resolution feature fusion network architecture which exploits densely connected deconvolution layers with skip connections, and can learn more effective features for small-size object; 2) We frame the traffic sign detection as a spatial sequence classification and regression task, and propose a vertical spatial sequence attention (VSSA) module to gain more context information for better detection performance. To comprehensively evaluate the proposed method, we do experiments on several traffic sign datasets as well as the general object detection dataset and the results have shown the effectiveness of our proposed method.

show abstract

A Boosted Multi-Task Model for Pedestrian Detection With Occlusion Handling

Cited by 31 publications

References 42 publications

Image Haze Removal Algorithm Based on Nonsubsampled Contourlet Transform

Image Haze Removal Algorithm Based on Nonsubsampled Contourlet Transform

Path Smoothing Techniques in Robot Navigation: State-of-the-Art, Current and Future Challenges

VSSA-NET: Vertical Spatial Sequence Attention Network for Traffic Sign Detection

Contact Info

Product

Resources

About