Training-Free, Generic Object Detection Using Locally Adaptive Regression Kernels

Abstract

Abstract-We present a generic detection/localization algorithm capable of searching for a visual object of interest without training. The proposed method operates using a single example of an object of interest to find similar matches, does not require prior knowledge (learning) about objects being sought, and does not require any preprocessing step or segmentation of a target image. Our method is based on the computation of local regression kernels as descriptors from a query, which measure the likeness of a pixel to its surroundings. Salient features are extracted from said descriptors and compared against analogous features from the target image. This comparison is done using a matrix generalization of the cosine similarity measure. We illustrate optimality properties of the algorithm using a naive-Bayes framework. The algorithm yields a scalar resemblance map, indicating the likelihood of similarity between the query and all patches in the target image. By employing nonparametric significance tests and nonmaxima suppression, we detect the presence and location of objects similar to the given query. The approach is extended to account for large variations in scale and rotation. High performance is demonstrated on several challenging data sets, indicating successful detection of objects in diverse contexts and under different imaging conditions.

Local structure preserving sparse coding for infrared target recognition

“…Besides, LSSM is compared with other general target detection method [34,35], which uses a robust LARK feature to implement entire matching with a single template, and has good capability to detect human faces and targets with simple shape and compact structure.…”

“…Thus, we not only measure among the LSc/KSc/LSPSc/K-LSPSc-based LSSM models and the part-based sparse representation method [52] by using the simple car template set in Fig 14(B), but also compare LSSM against the training-free method [34,35] by using a single template of the side view of car. Fig 15(B) shows the results of car detection.…”

“…Because of the imaging characteristics (noise and fuzzy details) in infrared images and use of the simple template set, its similarity discrimination between different car types has low fault-tolerance and adaptability. The training-free method in [34,35] loses the targets in changing imaging angles due to the single template. LSc and KSc mostly pay attention to sparse representation of the test sample, the local features consistent with the template set are detected as a target, so the false positives are high but the false negatives are relatively low.…”

Stereo object tracking with fusion of texture, color and disparity information

“…Therefore, various image texture descriptors can be employed for finding which of the remaining candidate object ROIs is most similar to the object appearance model. In this paper, we have chosen to use Local Steering Kernel (LSK) descriptors, which were employed successfully in [16] for generic object detection and in [17] for monocular object tracking, due to their robustness in the appearance changes that the object undergoes between successive frames. LSKs are local image texture descriptors which measure the similarity of an image pixel to its surrounding ones.…”

“…In this paper, we present an appearance-based tracking algorithm, which exploits stereo information obtained from the disparity maps of the left and right channels acquired by an uncalibrated stereo camera. The proposed framework combines a representation for the object texture based on Local Steering Kernel (LSK) descriptors [16], color information and disparity information. LSKs are local texture descriptors, which fit a Gaussian function over a local image region around an image pixel by elongating and steering the function according to the direction and intensity of the image edges.…”