Automatic image stitching using SIFT

Li, Yanfang; Wang, Yaming; Huang, Wenqing; Zhang, Zuoli

doi:10.1109/icalip.2008.4589984

Cited by 26 publications

(7 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…9 discussion will primarily focus on the performance evaluation of our proposed method in multiple wild conditions and some sample results. Here in this section we compare and benchmark our proposed method along with other image-stitching mechanisms(SIFT [13], ORB [8], KAZE [14], BRISK [15] & SURF [16]) with 4 main evaluation criterias, i.e PSNR, SSIM, Avg. Latency Time [52], Feature-Matching rate.…”

Section: Training and Experimentation Detailsmentioning

confidence: 99%

“…Latency Time [52], Feature-Matching rate. 6 All the above-stated imagestitching modules [8], [13]- [16] along with ours are subjected to multiple wild conditions, and the performance of each method is recorded in these wild conditions and evaluated. Five different wild conditions are considered for this benchmarking analysis, namely 1) Rotational Variation, 2) Resolution & Orientational(portrait & landscape) Variation, 3) Salt & Pepper Noise, 4) Manipulating % of common/matching area between input stereo images and 5) Color & Lumination/Intensity variation.…”

Section: Training and Experimentation Detailsmentioning

confidence: 99%

“…The final test variations in orientational differences). Here, we thoroughly benchmark the proposed method (l,r-Stitch Unit) along with other alternative image-stitching methods (SIFT [13], ORB [8], SURF [16], KAZE [14], BRISK [15] (refer to Column 1)) on a ''resolution-scale/Orientational variance wild-condition'' dataset. In this benchmarking analysis, we evaluate the performance of each image-stitching method based on PSNR, Mean-SSIM [52], FM-Rate evaluation-metrics (Column 2).…”

Section: Training and Experimentation Detailsmentioning

confidence: 99%

See 2 more Smart Citations

l, r-Stitch Unit: Encoder-Decoder-CNN Based Image-Mosaicing Mechanism for Stitching Non-Homogeneous Image Sequences

Chilukuri

Padala

Padala³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Image-stitching (or) mosaicing is considered an active research-topic with numerous use-cases in computer-vision, AR/VR, computer-graphics domains, but maintaining homogeneity among the input image sequences during the stitching/mosaicing process is considered as a primary-limitation & majordisadvantage. To tackle these limitations, this article has introduced a robust and reliable image stitching methodology (l,r-Stitch Unit), which considers multiple non-homogeneous image sequences as input to generate a reliable panoramically stitched wide view as the final output. The l,r-Stitch Unit further consists of a pre-processing, post-processing sub-modules & a l,r-PanoED-network, where each submodule is a robust ensemble of several deep-learning, computer-vision & image-handling techniques. This article has also introduced a novel convolutional-encoder-decoder deep-neural-network (l,r-PanoEDnetwork) with a unique split-encoding-network methodology, to stitch non-coherent input left, right stereo image pairs. The encoder-network of the proposed l,r-PanoED extracts semantically rich deep-featuremaps from the input to stitch/map them into a wide-panoramic domain, the feature-extraction & featuremapping operations are performed simultaneously in the l,r-PanoED's encoder-network based on the split-encoding-network methodology. The decoder-network of l,r-PanoED adaptively reconstructs the output panoramic-view from the encoder networks' bottle-neck feature-maps. The proposed l,r-Stitch Unit has been rigorously benchmarked with alternative image-stitching methodologies on our custom-built traffic dataset and several other public-datasets. Multiple evaluation metrics (SSIM, PSNR, MSE, L α,β,γ , FM-rate, Average-latency-time) & wild-Conditions (rotational/color/intensity variances, noise, etc) were considered during the benchmarking analysis, and based on the results, our proposed method has outperformed among other image-stitching methodologies and has proved to be effective even in wild non-homogeneous inputs.INDEX TERMS Deep feature extraction, encoder-decoder cnn, image mosaicing, multi-image registration, non-homogeneous image stitching.

show abstract

Section: Training and Experimentation Detailsmentioning

confidence: 99%

Section: Training and Experimentation Detailsmentioning

confidence: 99%

Section: Training and Experimentation Detailsmentioning

confidence: 99%

See 1 more Smart Citation

l, r-Stitch Unit: Encoder-Decoder-CNN Based Image-Mosaicing Mechanism for Stitching Non-Homogeneous Image Sequences

Chilukuri

Padala

Padala³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…SIFTfeatures are located at the scale-space maxima/minima of the differences between Gaussian functions, which keep the rotation, scale, or illumination invariant. ey are robust in terms of vision changes, affine changes, and noise [35]. SIFT feature matching mainly includes the following three steps.…”

Section: Sift Feature Matchingmentioning

confidence: 99%

Dynamic Pavement Distress Image Stitching Based on Fine-Grained Feature Matching

Weng

Liu

et al. 2020

Journal of Advanced Transportation

View full text Add to dashboard Cite

Camera-based pavement distress detection plays an important role in pavement maintenance. Duplicate collections for the same distress and multiple overlaps of defects are both practical problems that greatly affect the detection results. In this paper, we propose a fine-grained feature-matching and image-stitching method for pavement distress detection to eliminate duplications and visually demonstrates local pavement distress. The original images are processed through a hierarchical structure, including rough data filtering, feature matching, and image stitching. The original data are firstly filtered based on the global position system (GPS) information, which can avoid full-dataset comparison and improve the calculating efficiency. A scale-invariant feature transform is introduced for feature matching based on the extracted key regions using spectral saliency mapping and bounding boxes. Two parameters: the mean Euclidean distance (MEuD) and the matching rate (MCR) are constructed to identify the duplication between two images. A support vector machine is then applied to determine the threshold of MEuD and MCR. This paper further discusses the correlation between the sampling frequency and the number of detection vehicles. The method provided can effectively solve the problem of duplications in pavement distress detection and enhances the feasibility of multivehicle pavement distress detection based on images.

show abstract

“…The quality and robustness of this method is tested using three-dimensional rotational image. Yanfang [5] examined about automatic image stitching which applies the picture arrangement in any event even for noisy images. So, he used invariant features for fully automatic image which mainly had two parts which were image matching and image blending.…”

Section: Previous Workmentioning

confidence: 99%

Panoramic Image Stitching: A Survey

Bhasker¹

2020

IJMTST

View full text Add to dashboard Cite

This electronic document is a report on Image Stitching. Image stitching is the process of creating an image panorama from a given set of images that have some common(overlapping) area in them. Previous researches done on this topic show that there is still a lot of scope for improvement in this field as although we are able to achieve good results but we haven’t really been able to achieve perfection. There are a lot of factors that are to be blamed here. While Stitching Images, there could be many challenges such as images being corrupt by noise and/or presence of parallax in the images. Image Stitching process is divided into 5 major steps: Image Registration, Feature Detection, Feature Matching, Homography Estimation and Image Blending. In this document we are going to discuss the current status of image processing techniques and what are the challenges being faced.

show abstract

Automatic image stitching using SIFT

Cited by 26 publications

References 7 publications

l, r-Stitch Unit: Encoder-Decoder-CNN Based Image-Mosaicing Mechanism for Stitching Non-Homogeneous Image Sequences

l, r-Stitch Unit: Encoder-Decoder-CNN Based Image-Mosaicing Mechanism for Stitching Non-Homogeneous Image Sequences

Dynamic Pavement Distress Image Stitching Based on Fine-Grained Feature Matching

Panoramic Image Stitching: A Survey

Contact Info

Product

Resources

About