Adaptive Objectness for Object Tracking

Abstract

Object tracking is a long standing problem in vision. While great efforts have been spent to improve tracking performance, a simple yet reliable prior knowledge is left unexploited: the target object in tracking must be an object other than non-object. The recently proposed and popularized objectness measure provides a natural way to model such prior in visual tracking. Thus motivated, in this paper we propose to adapt objectness for visual object tracking. Instead of directly applying an existing objectness measure that is generic and handles various objects and environments, we adapt it to be compatible to the specific tracking sequence and object. More specifically, we use the newly proposed BING objectness as the base, and then train an object-adaptive objectness for each tracking task. The training is implemented by using an adaptive support vector machine that integrates information from the specific tracking target into the BING measure. We emphasize that the benefit of the proposed adaptive objectness, named ADOBING, is generic. To show this, we combine ADOBING with seven top performed trackers in recent evaluations. We run the ADOBING-enhanced trackers with their base trackers on two popular benchmarks, the CVPR2013 benchmark (50 sequences) and the Princeton Tracking Benchmark (100 sequences). On both benchmarks, our methods not only consistently improve the base trackers, but also achieve the best known performances. Noting that the way we integrate objectness in visual tracking is generic and straightforward, we expect even more improvement by using tracker-specific objectness

Beyond Local Search: Tracking Objects Everywhere with Instance-Specific Proposals

“…A straightforward strategy, i.e., linear combination of the original tracking confidence and an adaptive objectness score based on BING [10] is employed in [25]. In [20], a detection proposal scheme is applied as a post-processing step, mainly to improve the tracker's adaptability to scale and aspect ratio changes.…”

Robust Scale Adaptive Visual Tracking with Correlation Filters

“…To improve the computational efficiency of object detection, several proposal generators were proposed recently, such as BING [37] and EdgeBoxes [26]. Compared with other existing proposal generators, EdgeBoxes has the advantages of high computational efficiency, high quality of proposals, and flexible parameter setting without training.…”

“…However, most of existing trackers pay little attention to generating high-quality candidate proposals, which are important for improving tracking accuracy. Only few object tracking methods with object proposals [36][37][38][39][40] were proposed recently. Zhu et al [36] presented the EBT tracker that searches for randomly moving objects in the entire image instead of a local search window with object proposals generated by EdgeBoxes method.…”

“…Zhu et al [36] presented the EBT tracker that searches for randomly moving objects in the entire image instead of a local search window with object proposals generated by EdgeBoxes method. Liang et al [37] proposed to train an object-adaptive objectness for each tracking task with BING generator. Kwon and Lee [38] presented a novel tracking system based on edge-based object proposal and data association.…”

Online deep transfer learning applied to building quality assessment robots

“…Being able to perceive an object before it is recognized, is related to bottom-up visual attention. Under the definition of saliency, related research is divided into three categories: fixed forecasting [29], salient object detection [30] and objectness proposal generation [31][32][33], which has evolved considerably in the last two decades, especially since 2007 [2,34].…”