Ufuk Sakarya

A short survey of hyperspectral remote sensing applications in agriculture

Hyperspectral sensors are devices that acquire images over hundreds of spectral bands, thereby enabling the extraction of spectral signatures for objects or materials observed. Hyperspectral remote sensing has been used over a wide range of applications, such as agriculture, forestry, geology, ecological monitoring and disaster monitoring. In this paper, the specific application of hyperspectral remote sensing to agriculture is examined. The technological development of agricultural methods is of critical importance as the worlds population is anticipated to continuously rise much beyond the current number of 7 billion. One area upon which hyperspectral sensing can yield considerable impact is that of precision agriculture - the use of observations to optimize the use of resources and management of farming practices. For example, hyperspectral image processing is used in the monitoring of plant diseases, insect pests and invasive plant species; the estimation of crop yield; and the fine classification of crop distributions. This paper also presents a detailed overview of hyperspectral data processing techniques and suggestions for advancing the agricultural applications of hyperspectral technologies in Turkey.

Video scene detection using graph-based representations

One of the fundamental steps in organizing videos is to parse it in smaller descriptive parts. One way of realizing this step is to obtain shot or scene information. One or more consecutive semantically correlated shots sharing the same content construct video scenes. On the other hand, video scenes are different from the shots in the sense of their boundary definitions; video scenes have semantic boundaries and shots are defined with physical boundaries. In this paper, we concentrate on developing a fast, as well as well-performed video scene detection method. Our graph partition based video scene boundary detection approach, in which multiple features extracted from the video, determines the video scene boundaries through an unsupervised clustering procedure. For each video shot to shot comparison feature, a one-dimensional signal is constructed by graph partitions obtained from the similarity matrix in a temporal interval. After each one-dimensional signal is filtered, an unsupervised clustering is conducted for finding video scene boundaries. We adopt two different graph-based approaches in a single framework in order to find video scene boundaries. The proposed graph-based video scene boundary detection method is evaluated and compared with the graph-based video scene detection method presented in literature.

An improved method of photometric stereo using local shape from shading

Abstract This paper presents an improved photometric stereo (PS) method by integrating it with a local shape from shading (SFS) algorithm. PS produces the initial estimate of image for the global accuracy and also provides the recovery of albedo, SFS supplies the more detailed information within each homogeneous area. The quality of depth obtained by integrating PS and SFS is compared with the real depth using absolute dept error function, and the improvement ranging from 2.3 to 14% over PS is obtained.

Graph Partition Based Scene Boundary Detection

In this paper a graph partition based scene boundary detection method is proposed. Multiple features extracted from the video are considered for the determination of the scene boundaries in an unsupervised clustering procedure. For each video shot to shot comparison feature, one-dimensional signal is constructed by graph partitions obtained from the similarity matrix in a temporal interval. After each one-dimensional signal is filtered, k-means clustering is conducted for finding scene boundaries. The proposed graph-based scene boundary detection method is evaluated and compared with the graph-based scene detection method presented in literature.

Dominant sets based movie scene detection

Multimedia indexing and retrieval has become a challenging topic in organizing huge amount of multimedia data. This problem is not a trivial task for large visual databases; hence, segmentation into low- and high-level temporal video segments might improve the realization of this task. In this paper, we introduce a weighted undirected graph-based movie scene detection approach to detect semantically meaningful temporal video segments. The method is based on the idea of finding the dominant scene of the video according to the selected low-level feature. The proposed method starts from obtaining the most reliable solution first and exploit each solution in the subsequent steps recursively. The dominant movie scene boundary, which can be the highest probability to be the correct one, is determined and this scene boundary information is also exploited in the subsequent steps. We handle two partitioning strategies to determine the boundaries of the remaining scenes. One is a tree-based strategy and the other is an order-based strategy. The proposed dominant sets based movie scene detection method is compared with the graph-based video scene detection methods presented in literature.

Graph-based multilevel temporal video segmentation

This paper presents a graph-based multilevel temporal video segmentation method. In each level of the segmentation, a weighted undirected graph structure is implemented. The graph is partitioned into clusters which represent the segments of a video. Three low-level features are used in the calculation of temporal segments’ similarities: visual content, motion content and shot duration. Our strength factor approach contributes to the results by improving the efficiency of the proposed method. Experiments show that the proposed video scene detection method gives promising results in order to organize videos without human intervention.

Graph-based multilevel temporal segmentation of scripted content videos

This paper concentrates on a graph-based multilevel temporal segmentation method for scripted content videos. In each level of the segmentation, a similarity matrix of frame strings, which are series of consecutive video frames, is constructed by using temporal and spatial contents of frame strings. A strength factor is estimated for each frame string by using a priori information of a scripted content. According to the similarity matrix reevaluated from a strength function derived by the strength factors, a weighted undirected graph structure is implemented. The graph is partitioned to clusters, which represent segments of a video. The resulting structure defines a hierarchically segmented video tree. Comparative performance results of different types of scripted content videos are demonstrated.

A graph-based approach for video scene detection

In this paper, a graph-based method for video scene detection is proposed. The method is based on a weighted undirected graph. Each shot is a vertex on the graph. Edge weights among the vertices are evaluated by using spatial and temporal similarities of shots. By using the complete information of the graph, a set of the vertices mostly similar to each other and dissimilar to the others is detected. Temporal continuity constraint is achieved on this set. This set is the first detected video scene. The vertices of the video scene are extracted from the graph and the process is repeated by a certain number. The certain number of the video scenes whose boundaries are determined are placed in the temporal domain. Each temporal part between two detected scenes is accepted as a video scene.

Classification on hyperspectral images using Enhanced Fisher Discriminant Criterion

Hyperspectral image processing has become an important research topic day by day. Due to the improvement in camera technology, the easiness in data acquisition has a result of born of new application areas. One of the research topics in hyperspectral image processing is dimension reduction. Dimension reduction is a widely used method in pattern recognition when dealing with high dimensional data. In this paper, a method based on enhanced Fisher discriminant criterion (EFDC),which is proposed by Gao et al. (Q. Gao, J.Liu, H.Zhang, J. Hou and X. Yang, “Enhanced fisher discriminant criterion for image recognition”, Pattern Recognition, vol. 45, pp. 3717-3724, 2012) is proposed for classification on hyperspectral images. In the proposed method, EFDC is used for dimension reduction. In the proposed method, a classification process on hyperspectral imagesis done by using dimension reduced data. According to the earliest experimental studies, the promising results are obtained for classification on hyperspectral images.

Automated region segmentation on cartridge case base

One of the significant problems encountered in criminology studies is the successful automated matching of fired cartridge cases, on the basis of the characteristic marks left on them by firearms. An intermediate step in the solution of this problem is the segmentation of certain regions that are defined on the cartridge case base. This paper describes a model-based method that performs segmentation of the cartridge case using surface height image of a center fire cartridge case base. The proposed method detects the location of the cartridge case base center and specific circular contours around it iteratively by projecting the problem to a one-dimensional feature space. In addition, the firing pin impression region is determined by utilizing an adaptive threshold that differentiates impression marks form primer region surface. Letters on the cartridge case base are also detected by using surface modeling and adaptive thresholding, in order to render the surface comparison operation robust against irrelevant surface features. Promising experimental results indicate the eligibility of the proposed method to be used for automated cartridge case base region segmentation process.