A Modified Blind Deconvolution Algorithm for Deblurring of Colored Images

Gupta, Anuj; Sharma, Manvinder; Singh, Sohni; Palta, Pankaj

doi:10.1007/978-981-15-2620-6_10

Cited by 3 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…in [7] propose incorporation of low con dence tracking lter with DeepSort to carry out vehicle tracking with the aim of minimising the false positive tracks and unreliable detections. Data association inside the model has been performed by training the model with the self-generated vehicle re-identi cation dataset UADETRAC [44]. In several initial frames, tracks with lower average detection con dence scores have been dropped.…”

Section: Literature Surveymentioning

confidence: 99%

SDSCF Tracker: An improved deep learning-based approach to execute target tracking

Gautam¹,

Singh

2023

Preprint

View full text Add to dashboard Cite

SDSCF tracker is a novel tracking via detection-based framework developed to address the problem of background clutter and reduced ID switches caused during tracking process. The entire mechanism is divided in three stages namely: detection stage followed by segmentation and tracking. Initially, the input sequence is fed to the improved YOLO-Lite detector to extract the primary bounding boxes. After the detection has been performed, all the objects inside the frames undergo segmentation to eliminate the redundancy and background clutter. By integrating instance segmentation post-detection and prior to tracking, the computational parameters reduce drastically for each frame. Next, the correlation filter-based tracker along with DeepSort performs object tracking. DeepSort performs very well on the frames containing detections even through lengthier stages of occlusion however, fails in case of similar looking objects resulting in ID switches. Correlation filter-based tracker counters the problem and keeps the track of each target even if it remains undetected in detection stage. New IoU’s for bounding boxes tracked by correlation tracker and bounding boxes tracked by DeepSort are computed and based on new IoU obtained, decision is made weather the target ID from DeepSort or correlation tracker is to be considered thereby preventing ID switching. Experimental evaluation carried out on MOT15, MOT16 and MOT17 shows that the proposed framework reduces the amount of ID switches by almost 53 % achieving highest MOTA and MOTP of 69.6% and 84.7% respectively.

show abstract

Section: Literature Surveymentioning

confidence: 99%

SDSCF Tracker: An improved deep learning-based approach to execute target tracking

Gautam¹,

Singh

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…There is significant reduction in the threshold leakage current due to the stack effect when all the stacked transistors are together turned off. Figure 4 shows the forced stack inverter containing two pull-up and pull-down transistors [27]. As this cell has two bitlines (bitline and bitline'), depending upon the value which is stored in SRAM cell, leakage current differs [18].…”

Section: Forced Stackmentioning

confidence: 99%

Implementation and Modeling of Low Power Sleepy Stack Sram

Kakkar¹

2022

joas

View full text Add to dashboard Cite

For the future technologies in which the devices and circuits are integrating more, low power consuming devices are needed. Mostly the reduction of power dissipation work is concentrated on switching and leakage current. However, sub threshold current is also a big factor which leads to power consumption especially for memories. In this paper, leakage power of SRAM memory cell is reduced by power gated sleepy stack structure which leads to lesser power dissipation. The power dissipation is reduced to 226 µW with proposed technique compared with power dissipation of conventional 6T SRAM cell which had 740 µW. With lesser power dissipation the circuit can have more battery backup and lesser heat emission

show abstract

A Comprehensive Review on Algorithms of Image Processing for Autonomous and Electric Vehicles

Gollapudi,

Bhaumik,

Pandey

et al. 2023

Handbook of Research on Thrust Technologies’ Effect on Image Processing

View full text Add to dashboard Cite

The development of autonomous electric vehicles has gained significant attention due to their potential to reduce carbon emissions and improve road safety. Image processing has become an important tool in the development of these vehicles, enabling them to detect and respond to objects and obstacles in their environment. In this review paper, we explore the use of image processing in electric vehicles and driverless cars, with a focus on the various techniques proposed by authors. The comparison of the performance and effectiveness of different approaches, including deep learning, computer vision, and sensor fusion, in detecting and recognizing objects in the environment. Our review highlights the advantages and limitations of each technique and their potential for future development in the field of electric vehicles. Overall, image processing has shown to be a promising solution for the development of safe and efficient autonomous electric vehicles.

show abstract

A Modified Blind Deconvolution Algorithm for Deblurring of Colored Images

Cited by 3 publications

References 13 publications

SDSCF Tracker: An improved deep learning-based approach to execute target tracking

SDSCF Tracker: An improved deep learning-based approach to execute target tracking

Implementation and Modeling of Low Power Sleepy Stack Sram

A Comprehensive Review on Algorithms of Image Processing for Autonomous and Electric Vehicles

Contact Info

Product

Resources

About