Eric Dahai Cheng

Tracking people across disjoint camera views by an illumination-tolerant appearance representation

Tracking single individuals as they move across disjoint camera views is a challenging task since their appearance may vary significantly between views. Major changes in appearance are due to different and varying illumination conditions and the deformable geometry of people. These effects are hard to estimate and take into account in real-life applications. Thus, in this paper we propose an illumination-tolerant appearance representation, which is capable of coping with the typical illumination changes occurring in surveillance scenarios. The appearance representation is based on an online k-means colour clustering algorithm, a data-adaptive intensity transformation and the incremental use of frames. A similarity measurement is also introduced to compare the appearance representations of any two arbitrary individuals. Post-matching integration of the matching decision along the individuals‘ tracks is performed in order to improve reliability and robustness of matching. Once matching is provided for any two views of a single individual, its tracking across disjoint cameras derives straightforwardly. Experimental results presented in this paper from a real surveillance camera network show the effectiveness of the proposed method.

Multi-Frame Moving Object Track Matching Based on an Incremental Major Color Spectrum Histogram Matching Algorithm

In this paper, a Major Color Spectrum Histogram Representation (MCSHR) is introduced to represent a moving object by using a normalized geometric distance between two points in the RGB space. Then, an Incremental Major Color Representation Algorithm is proposed to cope with small pose changes occurring along the track. Finally, a two directional similarity measurement based on the major colors is used to measure the similarity of any two given moving objects in multiple integrated frames. Experimental results show that with a few (4 or 5) frames MCSHR integration, the proposed Incremental MCSHR algorithm can make matching more robust and reliable than single frame matching, especially for small pose changes. The major color representation algorithm based on the introduced color distance can represent moving objects accurately with a limited number of colors and the frequency of each major color. The similarity of a same moving object in two different tracks has improved from 85% to 97% with the number of integrated frames increasing from 1 to 5, while the similarity of two different moving objects has been kept as low as 9% to 19%.

Matching of Objects Moving Across Disjoint Cameras

Matching of single individuals as they move across disjoint camera views is a challenging task in video surveillance. In this paper, we present a novel algorithm capable of matching single individuals in such a scenario based on appearance features. In order to reduce the variable illumination effects in a typical disjoint camera environment, a cumulative color histogram transformation is first applied to the segmented moving object. Then, an incremental major color spectrum histogram representation (IMCSHR) is used to represent the appearance of a moving object and cope with small pose changes occurring along the track. An IMCHSR-based similarity measurement algorithm is also proposed to measure the similarity of any two segmented moving objects. A final step of post-matching integration along the objects track is eventually applied. Experimental results show that the proposed approach proved capable of providing correct matching in typical situations.

Track matching over disjoint camera views based on an incremental major color spectrum histogram

Matching tracks from a single individual across disjoint camera views is a challenging task in video surveillance. In this paper, a major color spectrum histogram representation (MCSHR) is introduced to represent a moving object by using a normalized distance between two points in the RGB space. Then, an incremental MCSHR is proposed to cope with small pose changes and segmentation errors occurring along the track. Finally, a similarity measurement algorithm is proposed based on the incremental MCSHR to measure the similarity of any two tracked moving objects. The proposed similarity measurement algorithm proved capable of measuring the similarity of the two moving objects accurately. Experimental results show that with three to five frames integration, the proposed incremental MCSHR algorithm can make matching more robust and reliable than single-frame matching, especially for small pose changes. The matching performance is not obviously improved instead when the number of integration is more than five. The similarity of a same moving object in two different tracks has been improved from 92% to 95% with the integration number increased from three to five, while two different moving objects have been easily discriminated. The proposed algorithm can be used to match tracks from single individuals in camera networks, which do not provide full coverage of the monitored space.

Mitigating the Effects of Variable Illumination for Tracking across Disjoint Camera Views

Tracking people by their appearance across disjoint camera views is challenging since appearance may vary significantly across such views. This problem has been tackled in the past by computing intensity transfer functions between each camera pair during an initial training stage. However, in real-life situations, intensity transfer functions depend not only on the camera pair, but also on the actual illumination at pixel-wise resolution and may prove impractical to estimate to a satisfactory extent. For this reason, in this paper we propose an appearance representation for people tracking capable of coping with the typical illumination changes occurring in a surveillance scenario. Our appearance representation is based on an online K-means color clustering algorithm, a fixed, data-dependent intensity transformation, and the incremental use of frames. Moreover, a similarity measurement is proposed to match the appearance representations of any two given moving objects along sequences of frames. Experimental results presented in this paper show that the proposed methods provides a viable while effective approach for tracking people across disjoint camera views in typical surveillance scenarios.

Disjoint track matching based on a major color spectrum histogram representation

A disjoint track matching algorithm is proposed based on major color spectrum histogram representation (MCSHR) matching and post-matching integration algorithms; this algorithm is useful for reconnecting broken tracks due to occlusions and potentially useful for tracking a single object across multiple, disjoint cameras. An incremental MCSHR (IMCSHR) matching algorithm is also proposed to cope with small pose changes occurring along the track. First, an MCSHR is introduced to represent a moving object by its most frequent colors. Then a two-directional (2-D) similarity measurement algorithm based on the most similar major color searching algorithm is proposed to measure the similarity of the two given moving objects by using IMCSHR in a few frames. Last, our track matching algorithm extends the multiframe matching along the objects tracks by a post-matching integration algorithm. Experimental results have shown that the similarity of two tracks from the same moving objects has proven as high as 89 to 97%, while the similarity of two tracks from different moving objects has been kept as low as 14 to 54%. The post-matching integration algorithm has been proven to be able to make track matching more robust and reliable.

Stochastic boats generated acoustic target signal detection in time-frequency domain

This paper is devoted to theoretic algorithms development and experimental research of automatic target detection of acoustic signals, especially for boats generated signals. In this paper, an observation space is created by sampling and dividing input analog acoustic signal into multiple frames and each frame is transformed into frequency domain. In the created observation space, a median constant false alarm rate (MCFAR) and post detection integration algorithms have been proposed for an effective automatic target detection of boat generated acoustic signals, in which a low constant false alarm rate is kept with relative high detection rate. The proposed algorithms have been tested on real boat generated acoustic signals. The statistical analysis and experimental results showed that the proposed algorithm has kept a very low false alarm rate and relatively high detection rate.