JP3820935B2 - Traffic flow anomaly detection apparatus and method - Google Patents

Description

【００２２】
ここでσ²h,Aは上流の車両感知器で観測される車高の分散、σ²h,Bは上流の車両感知器で観測される車高の分散である。
同様に、上流の車両感知器で車長ｌAと検出された車長ｌの車両が、下流の車両感知器で車長ｌBと観測される確率は、下記(2)式で表される。
【００２３】
【数２】

【００２４】
ここでσ²l,Aは上流の車両感知器で観測される車長の分散、σ²l,Bは上流の車両感知器で観測される車長の分散である。
(a)コスト評価基準として車高又は車長の差を用いる場合
上流の車両感知器で車高ｈAと検出された車両が、下流の車両感知器で車高ｈBと検出される事後確率密度Ｐh(ｈa,ｈb)は、下記(3)式で表される。
【００２５】
【数３】

【００２６】
同様に、上流の車両感知器で車長ｌAと検出された車両が、下流の車両感知器で車長ｌBと検出される事後確率密度Ｐl(ｌa,ｌb)は、下記(4)式で表される。
【００２７】
【数４】

【００２８】
σ²h,A＋σ²h,B＝σ²hと表し、σ²l,A＋σ²l,B＝σ²lと書くと、前記(3)(4)式は、それぞれ、(5)(6)式のように書き換えられる。
【００２９】
【数５】

【００３０】
【数６】

【００３１】
(b) コスト評価基準として車高又は車長の比を用いる場合
前記(5)(6)式に代えて、次の(7)(8)式を用いる。
【００３２】
【数７】

【００３３】
【数８】

【００３４】
以上に掲げた確率密度の自然対数を「マッチコスト」という。車高のみを用いる場合の、上流の車両感知器で車高ｈAと検出された車両と、下流の車両感知器で車高ｈBと検出された車両とのマッチコストｄ(ｈa,ｈb)は、
ｄ(ｈa,ｈb)＝ln［Ｐh(ｈa,ｈb)］ (9)
となる。
車長のみを用いる場合は、上流の車両感知器で車長ｌAと検出された車両と、下流の車両感知器で車長ｌBと検出された車両とのマッチコストｄ(ｌa,ｌb)は、
ｄ(ｌa,ｌb)＝ln［Ｐl(ｌa,ｌb)］ (10)
となる。
【００３５】
車高と車長を併用する場合は、上流の車両感知器で車高ｈA、車長ｌAと検出された車両と、下流の車両感知器で車高ｈB、車長ｌBと検出された車両とのマッチコストｄ(ｈa,ｌa;ｈb,ｌb)は、
ｄ(ｈa,ｌa;ｈb,ｌb)
＝ln［Ｐh(ｈa,ｈb)］＋ln［Ｐl(ｌa,ｌb)］ (11)
となる。
【００３６】
マッチング判定部２２は、前記(9)(10)(11)式のいずれかによって、上流の車両感知器で感知した車両、下流の車両感知器で感知した車両の全組み合わせについて、マッチコストを算出する(ステップＳ３)。
次に、マッチング判定部２２は、「ギャップコスト」を取得する。このギャップコストは、車両感知器の特性に応じた定数として記憶されているものである。マッチコストとギャップコストとを総称して「スコア」という。
【００３７】
ギャップコストには、インターナルギャップコスト（ＩＧＣ）とイクスターナルギャップコスト（ＥＸＧＣ）との２種類がある。
ＩＧＣは、両地点の間で追い越しが発生してその順序が入れ替わってしまい、対応が付かないような場合に設定される。これは、車高、車長のいずれかが３σ以上離れることはなく、３σ以上離れるとそれは別の車両とみなすとの仮定に基づく。
【００３８】
車高のみを用いる場合、ＩＧＣの具体的な値を示すと、(12)式のようになる。
ｄ(ｈa,−)＝ｄ(−,ｈb)＝（１／２）ln［Ｐh(０,３σh)］
＝−（１／２）ln（（２π）^1/2σh）−９／４ (12)
式中１／２を用いているのは、ギャップコストを用いる場合は２本の枝を使うことになるので、枝１本分のコストにするためである（以下同じ）。
車長のみを用いる場合、ＩＧＣの具体的な値を示すと、(13)式のようになる。
【００３９】
ｄ(ｌa,−)＝ｄ(−,ｌb)＝（１／２）ln［Ｐl(０,３σl)］
＝−（１／２）ln（（２π）^1/2σl）−９／４ (13)
車高と車長を併用する場合は、ＩＧＣの具体的な値を示すと、(14)式のようになる。
ｄ(ｈa,−;−,−)＝ｄ(−,ｌa;−,−)
＝ｄ(−, −; hb,−)＝ｄ(−, −;−,ｌb)
＝（１／２）｛ln［Ｐh(０,３σh)］＋ln［Ｐl(０,０)］｝
＝（１／２）｛ln［Ｐh(０,０)］＋ln［Ｐl(０, ３σl)］｝
＝−（１／２）ln（２πσhσl）−９／４ (14)
ＥＸＧＣは、上流地点を通過した車両がまだ下流地点を通過せず、車両の対応が付けられない場合に設定する。このＥＸＧＣの値は、実際に、本装置設置後の初期設定等の時点で、目視などで最適なマッチングが得られていると確認された場合に、アライメントの最大スコアを算出し、その最大スコアに基づいて決定されるものである。
【００４０】
さらに、現実には対応し得ないと思われる車両間の対応スコアは−∞にしておくことも考えられる（例えば旅行時間が負になる、経験上推定される旅行時間と比べると、あまりにも短いあるいは長い、など）。
以上の各コストが得られると、マッチコスト又はギャップコストの和が最大となるように、上流の車両感知器で感知したｎ台の車両と、下流の車両感知器で感知したｍ台の車両との対応付けを行う。このため、２次元の文字列アライメント問題として定式化する。
【００４１】
上流地点を通過した車両をａ1，ａ2，ａ3，‥‥，ａnで表し、下流地点を通過した車両をｂ1，ｂ2，ｂ3，‥‥，ｂnで表す。行列（ａiｂj）(1<i<n,1<j<m)をアライメントと呼ぶ。２次元の文字列アライメント問題は、２次元格子状有向グラフ上の最長路問題に帰着できる（一般的な呼び方は「最短路問題」であるが、ここではコストの和の最長のパスを求めているので、「最長路問題」という）。図４は、２次元格子状有向グラフを描いた図である。図４では、車両ａiと車両ｂjとを対応させる斜めの枝が実線で表されている。この枝長は、前述したマッチコストｄ（(9)〜(11)式のいずれか）に相当する。枠の内側の縦横の破線枝は、車両ａiと車両ｂjとの対応が付かない場合を表し、その枝長は、前述したＩＧＣに相当する。枠の外側の一点鎖線の枝は、対応する車両がない場合を表し、その枝長は、前述したＥＸＧＣに相当する。
【００４２】
図４の左上の点から、右下の点に至るコストの和の最長のパスが、車両のもっともらしい対応付けを示す解となる。この最長路問題は、動的計画（ＤＰ;Dynamic Programming）法で解くことができる(ステップＳ４)（下記［１］［２］参照）。
［１］D. Gusfield. "Aigorithms on Strings, Trees, and Sequences." Cambridge University Prass, 1997．
［２］S.B.Needleman and C.D.Wunsch."A general method applicable to the search for similarities in the amino acid sequences of two proteins." Journal of Molecular Biology,48, pp.443-453, 1970．
例えば、ｎ＝３，ｍ＝４とし、最長路問題を解いた結果、図５に示すような経路（太い実線）が得られたとする。この図５から、車両ａ1はｂ1に対応し、車両ａ2と車両ｂ2は対応せず（インターナルギャップ）、車両ａ3はｂ3に対応し、車両ｂ4に対応するものがない（イクスターナルギャップ）、ことが分かる。この原因は、車両ａ2とａ3は上流地点を通過した後入れ替わった、と考えられ、車両ｂ4は途中の交差点から進入してきた若しくは車線間移動により入ってきた、と考えられる。
【００４３】
以上の解析結果を出力する(ステップＳ５)。そして、出力された結果に基づいて、一致する車両同士に着目して、旅行時間を推定することができる。
ここで、ＥＸＧＣの値を決定する方法を説明する。ＥＸＧＣの値をｇとおく。上流でｎ台車両が観測され、下流でｍ台の車両が観測されたとする。ただしｎ＜ｍとする。目視などにより、上流地点で観測された車両ａ1〜ａnは、下流地点において観測された車両ｂ1〜ｂnに対応していることが分かっているものとする。しかし、上流地点で比較的遅い時刻に観測された車両ａn+1〜ａｍは、下流地点の観測時点において、まだ下流に到達しておらず、対応するものがない。
【００４４】
このときのアライメントの、マッチング部分のスコアをＳ′（Ａ）、非マッチング部分のスコアをｇ・ｘ（Ａ）と書く。Ｓ′（Ａ）は車両感知器の実測値から算出される値である。ｇは求めたいＥＸＧＣの値であり、ｘ（Ａ）は非マッチング台数を示し、ｘ（Ａ）＝ｎ−ｍである。
ＥＸＧＣの値ｇを「最適なマッチングが得られている場合の、マッチング部分のスコアＳ′（Ａ）を、ｎ＋ｍ−ｘ（Ａ）」で割ったもの、と定義する。
【００４５】
ｇ＝Ｓ′（Ａ）／［ｎ＋ｍ−ｘ（Ａ）］ (15)
たとえば、ｎ＝４，ｍ＝３とした場合の２次元格子状有向グラフを描くと図６のようになる。図６において、マッチング部分のスコアＳ′（Ａ）、ＥＸＧＣの値ｇ・ｘ（Ａ）を示している。ただし、ｘ（Ａ）＝ｎ−ｍ＝４−３＝１となるので、図６でｇ・ｘ（Ａ）と示したものは、ｇそのものを示している。
この図６の例では、ＥＸＧＣの値ｇは、前記(15)に基づき、
ｇ＝Ｓ′（Ａ）／［４＋３−１］＝Ｓ′（Ａ）／６ (16)
となる。
【００４６】
実際には、上下流でマッチングが確認されている車両群を観測してＥＸＧＣの値ｇを求める、という処理を複数回行い、求められた複数のｇの平均をとり、この平均値を最終的にＥＸＧＣの値ｇとして決定すればよい。
前記のＩＧＣとＥＸＧＣとを使った実施形態では、最新時点側（観測時刻の遅いほう）の車両対応付け部分（ｍの最も大きいところのデータ）は、ＥＸＧＣの値に大きく依存してしまう。ＥＸＧＣの値は、前述したように統計的に求められる値なので、変動する。
【００４７】
そこで、時系列最新時点側のＥＸＧＣを必要としないようにアルゴリズムを拡張する方法を説明する。
前述したとおり、ＥＸＧＣの値ｇは、
ｇ＝Ｓ′（Ａ）／［ｎ＋ｍ−ｘ（Ａ）］ (15)
で表される。一方、トータルスコアＳ（Ａ，ｇ）は、
Ｓ（Ａ，ｇ）＝Ｓ′（Ａ）＋ｇ・ｘ（Ａ） (17)
で表される。(15)式を(17)式に代入すると、
Ｓ（Ａ，ｇ）
＝Ｓ′（Ａ）＋Ｓ′（Ａ）ｘ（Ａ）／［ｎ＋ｍ−ｘ（Ａ）］
＝（ｎ＋ｍ）Ｓ′（Ａ）／［ｎ＋ｍ−ｘ（Ａ）］ (18)
となる。ｎ＋ｍは一定なので、Ｓ′（Ａ）／［ｎ＋ｍ−ｘ（Ａ）］を最大にするようなパスが最適な解となる。
【００４８】
上に述べたことを図解すると、次のようになる。
図７は、時系列最新時点側のイクスターナルギャップを除いた２次元格子状有向グラフを描いた図である。この図７のグラフにおいて、上流側通過車両ａ1，‥‥，ａnの添え字をｉ（１≦ｉ≦ｎ）とし、最新時点側の対応点をｖiとする。各点ｖiでのアライメントの最大スコアを求め、そのスコアを（ｉ＋ｍ）−ｘ（Ａ）で割った値が最大になる点を最新時点側の対応点ｖi₀とする。
【００４９】
以上で、本発明の実施の形態を説明したが、本発明の実施は、前記の形態に限定されるものではない。例えば、本発明において、車長や車高のデータ以外に、カメラで車両の画像データを取得してアライメントに利用することができる。この場合、画像間のスコアを定める必要があるが、画像検索などの分野で考案されている「画像間の距離」、具体的には、マッチディスタンス（下記［３］参照）、ＥＭＤ(Earth Mover's Distance)（下記［４］参照）を利用することができる。
【００５０】
［３］M.Werman, S.Peieg, and A.Rosenfeld."A distance metric for multi-dimensional histgrams." Computer, Vision, Graphics, and Image Processing, 32, pp.328-336, 1985.
［４］Y.Rubner, C Tomasi, and L.J.Guibas."The Earth Mover's Distance as a Metric for Image Retrieval. "Technical Report STAN-CS-TN-98-86, Department of Computer Science, Stanford University, September 1998.
マッチディスタンスは、画像内の画素の色情報を利用した距離で、２つの画像ヒストグラムの累積ヒストグラム間のＬ1距離として与えられる。具体的には、各車両の後方より撮影した画像から、輝度のヒストグラムと色相のヒストグラムを作る。輝度のヒストグラムは、すべての画素を輝度より３２レベルに分け、度数は各レベルの画素数とする。色相のヒストグラムは色相を３０段階に分け、度数は、各段階に含まれる画素の彩度の総和とする。画像の距離は、輝度と色相のヒストグラムによる距離の加重和とした。
【００５１】
ＥＭＤは、マッチディスタンスを一般化した距離で、画素の色情報の他に位置情報も用いる。各画像の画素を色と位置の近さによってクラスタリングし（下記［５］参照）、それらの間の最小費用流として与えられる。今回は、各画像を１６クラスタにクラスタリングした。
［５］M.Inaba, H.Imai, and N.Katoh."Application of weighted Voronoi diagrams and randomization to variance-based k-clastering." In Proceedings of the 10th ACM Symposium on Computational Geometry, pp.332-339, 1994
車両ａiと車両ｂjとの画像間の距離をＤijとしたとき、アライメントのスコアＤtotalとして、前記(9)(10)(11)式のいずれかと、画像間の距離Ｄijとの線形和を採用する。
【００５２】
Ｄtotal＝ｄ(ｈa,ｌa;ｈb,ｌb) ＋λＤij (18)
ここで定数λは重み付け係数である。また、車長・車高のギャップコストをＧとし、実対応車両間の距離の最大値をＭとしたとき、総ギャップコストＧtotalは、
Ｇtotal＝Ｇ−λＭ／２ (19)
として与えられる。
【００５３】
また、前記の実施の形態では、車両観測地点は、２地点としていたが、これを任意の複数地点に拡張することも可能である。車両観測地点がｐ（ｐは２以上の整数）地点あれば、車両の対応付けをｐ次元アライメント問題に帰着させることが可能である。
以上のようにして、上流地点を通過したｎ台の車両と、下流地点を通過したｍ台の車両との対応付けが行われた。
【００５４】
次に、異常判定部２４の行う交通流の異常検知処理をフローチャート（図８）を用いて説明する。この異常検知処理は、上流地点を通過した車両と、下流地点を通過した車両との対応付けをするのに同期して、行う。
異常判定部２４は、上下流地点での対応付け結果を入力する(ステップＴ１)。そして、下流地点を通過した車両のうち、何割が上流地点を通過した車両と対応付けされているのかを調べる。この割合をマッチング率という。例えば、下流地点を通過したｍ台の車両のうち、ｐ台が、上流地点を通過した車両と対応するとすれば、マッチング率は、ｐ／ｍとなる。このマッチング率をしきい値と比較する。
【００５５】
このしきい値は、実際に道路上の突発事象が発生した時点前後のマッチング率のデータを記録しておき、本発明の実施により道路上の突発事象の発生を最も精度よく検知することができるような値に選べばよい。さらに、時間帯、曜日、催事のある日ない日など、過去のいろいろな条件での車線利用率のデータを蓄積し、時間帯や、曜日、催事の有無などに応じて、最適なしきい値を設定するようにしてもよい。
【００５６】
さらに、旅行時間を測定し、旅行時間が比較的短い場合、つまり自由流に近い場合、しきい値を比較的小さくし、旅行時間が比較的長い場合、つまり渋滞の場合、しきい値を比較的大きくする(ステップＴ２〜Ｔ４)。旅行時間に代えて、交通量、占有率に基づいて渋滞かどうかを判断してもよい。
自由流に近い場合、突発事象が発生していない平常時でも、マッチング率は比較的低めになる。したがって、しきい値を下げないと誤検知する可能性が高くなる。一方、渋滞時は、平常時でもマッチング率は比較的高くなる。したがって、しきい値を上げないと、検知漏れが多くなる。
【００５７】
このステップＴ２〜Ｔ４におけるしきい値の増減は、人為的に設定してもよいが、自動的に行うようにすることが、省力のために望ましい。
異常判定部２４は、マッチング率としきい値とを比較し(ステップＴ５)、しきい値よりも低ければ、上下流地点の間で突発事象が発生したと判断する(ステップＴ７)。しきい値より高ければ、さらに、過去（例えば１回前）の上下流地点を通過した車両の対応付で得られたマッチング率がしきい値よりも高かったかどうかを調べ(ステップＴ６)、高ければ異常なしと判断する。低ければ、突発事象が続いていると判断する。
【００５８】
このように、マッチング率が２回以上連続してしきい値よりも高い場合に、異常なしと判断するのは、突発事象が起こっても偶然マッチングした場合における誤った判断を避けるためである。
以上に説明した突発事象の発生が複数の区間で判定される場合がある。この場合は、各区間におけるマッチング率を比較して、もっともマッチング率の低い区間を突発事象発生区間として特定することができる。
【００５９】
図９は、突発事象発生区間を特定する処理を説明するためのフローチャートである。
まず、いままで説明した突発事象発生判定処理を、それぞれの監視対象道路区間１，２，‥‥，ｉ，‥‥で行う（ステップＷ１）。すべての監視対象道路区間１，２，‥‥，ｉで同処理が終了すれば（ステップＷ２のYES）、突発事象発生と判定された区間があるかどうか調べる（ステップＷ３）。そして、各区間で算出されたマッチング率を比較する（ステップＷ４）。このマッチング率が最小を示す区間を、突発事象発生区間と特定する（ステップＷ５）。
【００６０】
以下、マッチング率の逆数を「評価値」ということにする。すなわち、評価値＝１／（マッチング率）。
図１０は、５つの区間での検知処理結果から得られた評価値の時間推移を示すグラフである。このグラフによれば、事故は８時２０分に発生し、各区間１〜３での評価値が上がっている。特に区間２の評価値が最大であるので、区間２が突発事象発生区間と特定することができる。
【００６１】
以上のようにして突発事象の発生及びその発生区間が決定されると、交通管理センター１０は、可変表示板６，９に、突発事象の発生を表示し、路側ビーコン７を通して車両に突発事象の発生を通知する。
この通知にあたっては、前記評価値を複数のしきい値と比較する。１つは「検知しきい値」であり、他の１つは「注意しきい値」である。「検知しきい値」＞「注意しきい値」の関係がある。
【００６２】
評価値が検知しきい値を超えていれば突発事象の発生尤度が十分に高く「突発事象発生」と判断する。この検知しきい値が高すぎると検知漏れが多くなり、検知しきい値が低すぎると誤検知が増える。この検知しきい値は、検知漏れ率や誤検知率の実績に基づき、自動的に決定されるようにしてもよい。
検知しきい値を超えていなければ、この評価値を注意しきい値と比較する。注意しきい値を超えていれば、突発事象の発生尤度が中程度に高く、「突発事象の発生の可能性が高い注意状態」と判断する。
【００６３】
注意しきい値を超えていなければ、突発事象の発生尤度が低く、「突発事象の発生なし」と判断する。
「突発事象発生」と判定されていれば、交通管理センター１０の出力処理部２５は、可変表示板６，９に「この先事故・止まれ」のような運転者の警告を与えるメッセージを表示し、路側ビーコン７を通して車両にも危険区間である旨を通知する。
【００６４】
「突発事象の発生の可能性が高い注意状態」と判定されていれば、出力処理部２５は、可変表示板６，９に「前方注意」のように運転者の注意を喚起するようなメッセージを表示し、路側ビーコン７を通して車両にも走行注意区間である旨を通知する。
そして、これらの情報を通信回線を通して関係機関１３や放送局１４に連絡する。
【００６５】
なお、すでに道路工事などが予定され、交通流の異常が予想されている場合は、出力処理部２５は、当該時刻に突発事象の発生を判定しても、この判定に基づいて可変表示板６，９に突発事象の発生を表示することはなく、関係機関１３や放送局１４に連絡することもない。
以上で本発明の実施の形態を説明したが、本発明の実施は、前記に限られるものではない。前記の例では、高速道路を想定していたが、一般道路であってもよい。車線数が２車線の道路を想定したが、車線数は、２に限られるものではなく、１車線であっても３以上の車線であってもよい。
【００６６】
また、複数埋め込み式の車両感知器５に代えて、道路の脇に設置されるドップラー式の車両感知器を用いてもよい。また、道路にテレビカメラを設置して画像処理により車両通過台数、車高、車長、通過速度などを検知してもよい。
また、マッチング率を算出する方法として、他の公知の方法を採用てもよい。例えば、車両の画像を撮影し、画像処理を用いて車両の特徴、例えば色やプレートナンバーを認識する方法を採用してもよい。
【００６７】
【発明の効果】
以上のように本発明の交通流の異常検知装置によれば、道路上の突発事象の発生を精度よく検知することができる。
【図面の簡単な説明】
【図１】交通流の異常検知をするための交通流監視システムを示す概略図である。
【図２】交通管理センター１０のコンピュータ１１の機能ブロック図である。
【図３】マッチング判定部２２の行う車両群マッチング処理方法を説明するためのフローチャートである。
【図４】２次元格子状有向グラフを描いた図である。
【図５】ｎ＝３，ｍ＝４とし、最長路問題を解いた結果を示すための、２次元格子状有向グラフの図である。
【図６】ｎ＝４，ｍ＝３とし、車両ｂ4のみマッチングされていない場合の２次元格子状有向グラフである。
【図７】時系列最新時点側のイクスターナルギャップを必要としないアルゴリズムを説明するための、２次元格子状有向グラフを描いた図である。
【図８】異常判定部２４が行う突発事象発生を監視する処理を説明するためのフローチャートである。
【図９】突発事象発生区間を特定する処理を説明するためのフローチャートである。
【図１０】５つの区間での検知処理結果から得られた評価値の時間推移を示すグラフである。
【符号の説明】
１ 高速道路
２ 一般道路
３ 車両感知器
４ 一次処理装置
５ 車両感知器
６ 可変表示板
７ 路側ビーコン
９ 可変表示板
１０ 交通管理センター
１１ コンピュータ
１３ 関係機関
１４ 放送局
２２ マッチング判定部
２４ 異常判定部[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a traffic flow abnormality detection apparatus and method capable of collecting traffic measurement data by installing a vehicle detector or the like on a road, and detecting a traffic flow abnormality due to occurrence of a sudden event based on the traffic measurement data. Is.
[0002]
[Prior art]
When a sudden event such as a traffic accident or disaster occurs on the road, it is necessary to quickly detect an abnormality in the traffic flow based on the sudden event and notify the following vehicle or guide the following vehicle.
Conventionally, a camera is installed on a road and image processing is performed to detect an abnormality in a traffic flow (see JP-A-7-21488, JP-A-10-40490, etc.). It is expensive to install a camera over a wide area, and it is difficult to detect at night or in bad weather.
[0003]
In view of this, road traffic volume, vehicle speed, and the like are measured using vehicle detectors installed at various locations on the road, and traffic flow abnormalities are monitored based on these measured values.
According to this monitoring device, it is determined that an accident has occurred when the traffic has a small amount of traffic and the speed drops rapidly and the state continues for a certain period of time.
[0004]
[Problems to be solved by the invention]
However, in the monitoring device described above, since the determination is based on the traveling speed of the vehicle, there is a problem that it is difficult to distinguish when a sudden event occurs during a natural traffic jam, and the detection accuracy decreases.
Therefore, the inventor has paid attention to frequent lane changes when sudden events occur on the road. If you pay attention to a certain lane, as a result of the lane change, the vehicle may appear to have disappeared when moving to another lane, it may appear to have entered from another lane, or the order of vehicles may change as a result of overtaking. There are things to do.
[0005]
On the other hand, a technique for identifying a vehicle by installing a vehicle detector and a camera upstream and downstream of the road has been developed.
The present invention can detect a plurality of vehicles traveling on a road as a vehicle group, and can detect the occurrence of a sudden event on the road based on a change in arrangement in the vehicle group using a vehicle identification technology. It is an object to realize a traffic flow abnormality detection device and method.
[0006]
[Means for Solving the Problems]
The traffic flow abnormality detection device of the present invention is installed at a plurality of vehicle observation points, by associating vehicle feature amount observation means for observing the feature amount of a passing vehicle with vehicles passing through each vehicle observation point, When the matching degree of the alignment of the vehicle group (alignment), that is, the matching determination means for determining the matching rate, and the matching degree of the alignment of the vehicle group becomes smaller than the threshold based on the determination result of the matching determination means And an abnormality determination means for detecting the occurrence of a sudden event on the road between the vehicle observation points (claim 1).
[0007]
If there are no sudden incidents on the road, the alignment of the vehicle group will not change much, but if sudden incidents occur on the road, the lane will change frequently, and as a result, the vehicle will move to another lane and disappear. The alignment changes because it looks like it has come in, appears to have entered from another lane, or the order of vehicles changes as a result of overtaking.
Therefore, the feature amount of the vehicle is observed and the vehicles that have passed through a plurality of vehicle observation points are associated with each other, thereby checking the degree of alignment, that is, the matching rate. Based on this decrease in the degree of coincidence, an unexpected event on the road Can be detected.
[0008]
Reduction in degree of matching, Ru can be determined by comparison with a threshold value. This threshold value is used to record the degree of coincidence before and after the occurrence of the sudden event on the road, and the occurrence of the sudden event on the road can be detected with the highest accuracy by implementing the present invention. Choose a value.
A vehicle length, a vehicle height, a vehicle image, or the like can be used as the vehicle feature amount (claims 2 to 4 ).
[0009]
The threshold value is the optimum threshold value depending on the time zone, day of the week, the presence or absence of events, etc. May be set (claim 5 ).
The threshold value may be a value that is automatically determined and stored in accordance with traffic conditions (claim 6 ). In the traffic flow abnormality detection device of the present invention, the matching rate naturally decreases when there is no sudden event on the road, when the road is not congested, and when the road is congested, the matching rate Rises naturally. Therefore, when the road is not congested, the threshold is automatically lowered to reduce the false detection rate, and when the road is congested, the threshold is automatically increased to reduce detection omissions. To do.
[0010]
The traffic flow abnormality detection device of the present invention may further include information providing means for notifying the outside of the occurrence of the sudden event when the sudden event on the road is detected (Claim 7 ). . For example, information can be provided to the driver of the vehicle using communication means such as a roadside beacon, a mobile radio telephone, and broadcasting.
The information providing means may provide information to a vehicle traveling in the area or the section, or a vehicle expected to travel in the area or the section (Claim 8 ). This is intended to limit the vehicles that provide information to certain related vehicles.
[0011]
Information providing means, with respect to the event on the road that has already been scheduled, but it may also be not inform the outside even to detect the occurrence of the event. For example, when it is known that the lane is restricted from a certain time due to road construction or the like, even if an event is detected on the road in the construction section at that time, it is not notified to the outside. This is to prevent confusion caused by notifying outside.
The abnormality determination means performs stepwise determination according to the magnitude (likelihood) of the evaluation value that is the basis of the determination, and the information providing means depends on the result of the stepwise determination by the abnormality determination means. It is preferable to change the contents of the abnormality information (claim 9 ). Depending on the likelihood (certainty) of the occurrence of the sudden event, for example, by changing the contents of the information provision such as “future accident / stop”, “forward warning”, more appropriate information can be given to the driver.
[0012]
When the abnormality determination unit detects an abnormality in traffic flow in a plurality of road sections, the abnormality determination section may specify the abnormality occurrence section according to the magnitude of the evaluation value that is the basis of the determination (claim 10 ). By setting the section having the highest likelihood (certainty) of the occurrence of the sudden event as the abnormality occurrence section, it is possible to notify the subsequent driver and the like of the information on the occurrence section and the information on the avoidance route.
The traffic flow abnormality detection method according to the present invention (claim 11 ) is a method according to the same invention as the traffic flow abnormality detection device according to claim 1.
[0013]
DETAILED DESCRIPTION OF THE INVENTION
Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings, taking the traffic flow monitoring of an expressway as an example.
FIG. 1 is a schematic diagram showing a traffic flow monitoring system for detecting an abnormality in traffic flow.
Loop-embedded vehicle detectors 5 are installed on the two-lane highway 1 for each lane at intervals. An ultrasonic vehicle detector 3 that measures the vehicle height from above the vehicle is also installed for each lane. These vehicle detectors 3 and 5 are connected to the primary processing device 4. The primary processing device 4 detects the speed and height of each vehicle.
[0014]
In addition, the highway 1 is provided with a variable display board 6 for notifying the vehicle of accident information, road surface information, and the like. A roadside beacon 7 that performs bidirectional communication with the vehicle is also provided.
Further, the general road 2 connected to the expressway 1 is provided with a variable display board 9 for notifying the vehicle that is about to enter the expressway 1 of accident information and road surface information of the expressway 1.
[0015]
A computer inside the traffic management center 10 is connected to a primary processing device 4, a roadside beacon 7, a variable display board 6, and the like installed in each section through a wired communication network 12 (which may be a wireless communication network). .
Further, the computer is connected to related organizations 13 such as the Ministry of Construction, the National Police Agency, the Fire Department, etc. through a communication line, and is also connected to the broadcasting station 14 through the communication line.
FIG. 2 is a functional block diagram of the computer 11 of the traffic management center 10.
[0016]
Sensing signals from the vehicle detectors 3 and 5 are input to the input processing unit 21 of the computer 11 via the matching determination unit 22.
The input processing unit 21 calculates the maximum vehicle height of each vehicle based on the output of the vehicle detector 3 and measures the speed of the vehicle based on the output time difference between the two loops of the vehicle detector 5. The vehicle length is calculated based on the perception time. Since the vehicle height and the vehicle length are calculated every time the vehicle passes, a data string of one or more vehicle heights and vehicle lengths is obtained for each lane.
[0017]
A vehicle group matching processing method performed by the matching determination unit 22 of the computer 11 will be described with reference to a flowchart (FIG. 3).
In addition to the method described below, various methods are known as the vehicle group matching processing method. In the following, as an example, a method in which vehicle matching is reduced to a p-dimensional alignment problem is performed. (Kobayashi et al. “Annual Traffic Flow Analysis Algorithm Based on Two-point Vehicle Observation Information” (published on March 21, 2000, 72nd Algorithm Study Group, Information Processing Society of Japan))
[0018]
In the following, attention is focused on only one lane. A vehicle that has entered the lane from another lane and a vehicle that has exited the lane from the lane are treated in the same manner as a vehicle that has entered the lane from an intersection or a vehicle that has exited the intersection from the lane.
The vehicle height and vehicle length data sequence detected by the vehicle detectors 3 and 5 upstream in the traveling direction are input (step S1), and the vehicle height and vehicle length data sequence detected by the vehicle detectors 3 and 5 downstream in the traveling direction are input. (Step S2).
[0019]
The number of vehicles to be processed detected by the upstream vehicle sensor is n, the vehicle height data string is represented by hA1, hA2, hA3,..., HAn (represented by “hA” when representative), and the vehicle length data string. Is represented by lA1, lA2, lA3,..., LAn (represented by “lA” when representative). The number of vehicles to be processed detected by the downstream vehicle sensor is m, and the vehicle height data string is represented by hB1, hB2, hB3,..., HBm (represented by “hB” when represented), and the vehicle length data string. Is represented by lB1, lB2, lB3,..., LBm (represented by “lB” when representative).
[0020]
Assuming that the vehicle height h detected by the upstream vehicle detector is observed as the vehicle height hB at the downstream vehicle detector, the observation error of the vehicle detector follows a Gaussian distribution. Is expressed by the following equation (1).
[0021]
[Expression 1]

[0022]
Here, σ ² h, A is the dispersion of the vehicle height observed by the upstream vehicle sensor, and σ ² h, B is the dispersion of the vehicle height observed by the upstream vehicle sensor.
Similarly, the probability that a vehicle having a vehicle length l detected as a vehicle length lA by an upstream vehicle sensor is observed as a vehicle length lB by a downstream vehicle sensor is expressed by the following equation (2).
[0023]
[Expression 2]

[0024]
Here, σ ² l, A is the dispersion of the vehicle length observed by the upstream vehicle sensor, and σ ² l, B is the dispersion of the vehicle length observed by the upstream vehicle sensor.
(a) When the difference in vehicle height or vehicle length is used as a cost evaluation criterion A posterior probability density Ph in which a vehicle detected as a vehicle height hA by an upstream vehicle detector is detected as a vehicle height hB by a downstream vehicle detector (ha, hb) is expressed by the following equation (3).
[0025]
[Equation 3]

[0026]
Similarly, the posterior probability density Pl (la, lb) in which the vehicle detected as the vehicle length lA by the upstream vehicle detector is detected as the vehicle length lB by the downstream vehicle detector is expressed by the following equation (4). Is done.
[0027]
[Expression 4]

[0028]
When expressed as σ ² h, A + σ ² h, B = σ ² h, and written as σ ² l, A + σ ² l, B = σ ² l, the above-mentioned expressions (3) and (4) are respectively expressed as (5) (6 It can be rewritten as
[0029]
[Equation 5]

[0030]
[Formula 6]

[0031]
(b) When the ratio of vehicle height or vehicle length is used as the cost evaluation standard, the following equations (7) and (8) are used instead of the equations (5) and (6).
[0032]
[Expression 7]

[0033]
[Equation 8]

[0034]
The natural logarithm of the probability density listed above is called “match cost”. When only the vehicle height is used, the match cost d (ha, hb) between the vehicle detected as the vehicle height hA by the upstream vehicle detector and the vehicle detected as the vehicle height hB by the downstream vehicle detector is
d (ha, hb) = ln [Ph (ha, hb)] (9)
It becomes.
When only the vehicle length is used, the match cost d (la, lb) between the vehicle detected as the vehicle length lA by the upstream vehicle detector and the vehicle detected as the vehicle length 1B by the downstream vehicle detector is
d (la, lb) = ln [Pl (la, lb)] (10)
It becomes.
[0035]
When the vehicle height and the vehicle length are used in combination, the vehicle detected as the vehicle height hA and the vehicle length 1A by the upstream vehicle detector, and the vehicle detected as the vehicle height hB and the vehicle length 1B by the downstream vehicle detector Match cost d (ha, la; hb, lb) is
d (ha, la; hb, lb)
= Ln [Ph (ha, hb)] + ln [Pl (la, lb)] (11)
It becomes.
[0036]
The matching determination unit 22 calculates the match cost for all combinations of the vehicle sensed by the upstream vehicle sensor and the vehicle sensed by the downstream vehicle sensor, according to any of the formulas (9), (10), and (11). (Step S3).
Next, the matching determination unit 22 acquires “gap cost”. This gap cost is stored as a constant according to the characteristics of the vehicle detector. The match cost and the gap cost are collectively referred to as “score”.
[0037]
There are two types of gap cost: internal gap cost (IGC) and external gap cost (EXGC).
The IGC is set when an overtaking occurs between the two points and the order is changed and no correspondence can be obtained. This is based on the assumption that either the vehicle height or the vehicle length is not separated by 3σ or more, and that it is regarded as another vehicle when separated by 3σ or more.
[0038]
When only the vehicle height is used, the specific value of IGC is expressed as shown in equation (12).
d (ha, −) = d (−, hb) = (1/2) ln [Ph (0,3σh)]
=-(1/2) ln ((2π) ^1/2 σh) -9/4 (12)
The reason why 1/2 is used in the equation is that when using the gap cost, two branches are used, so that the cost is equivalent to one branch (the same applies hereinafter).
When only the vehicle length is used, the specific value of IGC is shown as equation (13).
[0039]
d (la, −) = d (−, lb) = (1/2) ln [Pl (0,3σl)]
=-(1/2) ln ((2π) ^1/2 σl) -9/4 (13)
In the case where the vehicle height and the vehicle length are used in combination, the specific value of IGC is shown in the equation (14).
d (ha,-;-,-) = d (-, la;-,-)
= D (-,-; hb,-) = d (-,-;-, lb)
= (1/2) {ln [Ph (0,3σh)] + ln [Pl (0,0)]}
= (1/2) {ln [Ph (0,0)] + ln [Pl (0,3σl)]}
=-(1/2) ln (2πσhσl) -9/4 (14)
EXGC is set when the vehicle that has passed through the upstream point has not yet passed through the downstream point and the vehicle cannot be dealt with. The EXGC value is calculated by calculating the maximum alignment score when it is confirmed that an optimum matching is obtained by visual inspection or the like at the time of initial setting after installation of the apparatus. It is determined based on
[0040]
Furthermore, the correspondence score between vehicles that cannot actually be handled may be set to −∞ (for example, the travel time becomes negative, which is too short compared with the travel time estimated from experience. Or long).
When each of the above costs is obtained, n vehicles sensed by the upstream vehicle sensor and m vehicles sensed by the downstream vehicle sensor so that the sum of the match cost or gap cost is maximized. Is associated. For this reason, it is formulated as a two-dimensional character string alignment problem.
[0041]
The vehicles that have passed the upstream point are represented by a1, a2, a3,..., An, and the vehicles that have passed the downstream point are represented by b1, b2, b3,. The matrix (aibj) (1 <i <n, 1 <j <m) is called alignment. The two-dimensional character string alignment problem can be reduced to the longest path problem on a two-dimensional grid directed graph (generally called the “shortest path problem”, but here the longest path of the sum of costs is obtained. (This is called the “longest road problem”). FIG. 4 is a diagram depicting a two-dimensional grid-like directed graph. In FIG. 4, diagonal branches that correspond to the vehicles ai and bj are represented by solid lines. This branch length corresponds to the above-mentioned match cost d (any one of the equations (9) to (11)). The vertical and horizontal broken lines inside the frame represent a case where the correspondence between the vehicle a i and the vehicle b j is not attached, and the length of the branch corresponds to the IGC described above. A one-dot chain line branch outside the frame represents a case where there is no corresponding vehicle, and the branch length corresponds to the above-described EXGC.
[0042]
The longest path of the sum of costs from the upper left point to the lower right point in FIG. 4 is a solution indicating a plausible association of vehicles. This longest path problem can be solved by a dynamic programming (DP) method (step S4) (see [1] and [2] below).
[1] D. Gusfield. “Aigorithms on Strings, Trees, and Sequences.” Cambridge University Prass, 1997.
[2] SBNeedleman and CDWunsch. “A general method applicable to the search for similarities in the amino acid sequences of two proteins.” Journal of Molecular Biology, 48, pp. 443-453, 1970.
For example, suppose that n = 3 and m = 4, and as a result of solving the longest path problem, a path (thick solid line) as shown in FIG. 5 is obtained. From FIG. 5, the vehicle a1 corresponds to b1, the vehicle a2 and the vehicle b2 do not correspond (internal gap), the vehicle a3 corresponds to b3, and there is nothing corresponding to the vehicle b4 (external gap). I understand. The cause is considered that the vehicles a2 and a3 have been switched after passing the upstream point, and the vehicle b4 has entered from an intermediate intersection or entered due to movement between lanes.
[0043]
The above analysis result is output (step S5). Based on the output result, the travel time can be estimated by paying attention to the matching vehicles.
Here, a method for determining the value of EXGC will be described. Let EXGC be g. Assume that n vehicles are observed upstream and m vehicles are observed downstream. However, n <m. It is assumed that the vehicles a1 to an observed at the upstream point correspond to the vehicles b1 to bn observed at the downstream point by visual observation or the like. However, the vehicles an + 1 to am observed at a relatively late time at the upstream point have not yet reached the downstream at the time of observation at the downstream point, and there is no corresponding one.
[0044]
At this time, the score of the matching portion of the alignment is written as S ′ (A), and the score of the non-matching portion is written as g · x (A). S ′ (A) is a value calculated from the actual measurement value of the vehicle detector. g is the value of EXGC to be obtained, x (A) indicates the number of non-matching, and x (A) = n−m.
The value g of EXGC is defined as “the score S ′ (A) of the matching portion when optimum matching is obtained, divided by n + mx (A)”.
[0045]
g = S ′ (A) / [n + mx− (A)] (15)
For example, FIG. 6 shows a two-dimensional grid-like directed graph when n = 4 and m = 3. In FIG. 6, the score S ′ (A) of the matching portion and the EXGC value g · x (A) are shown. However, since x (A) = n−m = 4−3 = 1, what is indicated as g · x (A) in FIG. 6 indicates g itself.
In the example of FIG. 6, the value g of EXGC is based on (15) above.
g = S ′ (A) / [4 + 3-1] = S ′ (A) / 6 (16)
It becomes.
[0046]
Actually, the process of obtaining the EXGC value g by observing the vehicle group whose matching is confirmed in the upstream and downstream is performed a plurality of times, and the average of the obtained plurality of g is taken and this average value is finally obtained. The EXGC value g may be determined as follows.
In the embodiment using the IGC and EXGC described above, the vehicle association portion (data having the largest m) on the latest time point side (the later observation time) greatly depends on the value of EXGC. Since the value of EXGC is a value that is statistically obtained as described above, it fluctuates.
[0047]
Therefore, a method for extending the algorithm so as not to require EXGC on the time series latest time point side will be described.
As mentioned above, EXGC value g is
g = S ′ (A) / [n + mx− (A)] (15)
It is represented by On the other hand, the total score S (A, g) is
S (A, g) = S ′ (A) + g · x (A) (17)
It is represented by Substituting equation (15) into equation (17),
S (A, g)
= S '(A) + S' (A) x (A) / [n + mx (A)]
= (N + m) S '(A) / [n + mx (A)] (18)
It becomes. Since n + m is constant, a path that maximizes S ′ (A) / [n + mx− (A)] is the optimal solution.
[0048]
Illustrating what has been said above:
FIG. 7 is a diagram depicting a two-dimensional grid-like directed graph excluding the external gap on the time series latest time point side. In the graph of FIG. 7, the subscripts of the upstream passing vehicles a1,..., An are i (1 ≦ i ≦ n), and the corresponding point on the latest time point side is vi. The maximum score of the alignment at each point vi is obtained, and the point where the value obtained by dividing the score by (i + m) −x (A) becomes the maximum is set as the corresponding point vi ₀ on the latest time point.
[0049]
Although the embodiments of the present invention have been described above, the embodiments of the present invention are not limited to the above-described embodiments. For example, in the present invention, in addition to vehicle length and vehicle height data, vehicle image data can be acquired by a camera and used for alignment. In this case, it is necessary to determine a score between images. “Distance between images” devised in the field of image search, specifically, match distance (see [3] below), EMD (Earth Mover's Distance) (see [4] below) can be used.
[0050]
[3] M. Werman, S. Peieg, and A. Rosenfeld. "A distance metric for multi-dimensional histgrams." Computer, Vision, Graphics, and Image Processing, 32, pp.328-336, 1985.
[4] Y.Rubner, C Tomasi, and LJGuibas. "The Earth Mover's Distance as a Metric for Image Retrieval." Technical Report STAN-CS-TN-98-86, Department of Computer Science, Stanford University, September 1998.
The match distance is a distance using the color information of the pixels in the image and is given as an L1 distance between the cumulative histograms of the two image histograms. Specifically, a luminance histogram and a hue histogram are created from images taken from the rear of each vehicle. In the luminance histogram, all pixels are divided into 32 levels from the luminance, and the frequency is the number of pixels at each level. The hue histogram divides the hue into 30 stages, and the frequency is the sum of the saturations of the pixels included in each stage. The image distance is the weighted sum of the distances based on the histogram of luminance and hue.
[0051]
EMD is a distance that generalizes match distance, and uses position information in addition to pixel color information. The pixels of each image are clustered by color and position proximity (see [5] below), given as the minimum cost flow between them. This time, each image was clustered into 16 clusters.
[5] M. Inaba, H. Imai, and N. Katoh. "Application of weighted Voronoi diagrams and randomization to variance-based k-clastering." In Proceedings of the 10th ACM Symposium on Computational Geometry, pp.332-339, 1994
When the distance between the images of the vehicle ai and the vehicle bj is Dij, a linear sum of any of the expressions (9), (10), and (11) and the distance Dij between the images is adopted as the alignment score Dtotal. .
[0052]
Dtotal = d (ha, la; hb, lb) + λDij (18)
Here, the constant λ is a weighting coefficient. In addition, when the gap cost of the vehicle length / height is G and the maximum distance between actual vehicles is M, the total gap cost Gtotal is
Gtotal = G-λM / 2 (19)
As given.
[0053]
In the above embodiment, the number of vehicle observation points is two. However, it is possible to extend this to any number of points. If the vehicle observation point is a p point (p is an integer of 2 or more), it is possible to reduce the vehicle association to the p-dimensional alignment problem.
As described above, the n vehicles that have passed the upstream point and the m vehicles that have passed the downstream point are associated with each other.
[0054]
Next, the traffic flow abnormality detection process performed by the abnormality determination unit 24 will be described with reference to a flowchart (FIG. 8). This abnormality detection process is performed in synchronization with the association between the vehicle that has passed the upstream point and the vehicle that has passed the downstream point.
The abnormality determination unit 24 inputs the association result at the upstream and downstream points (step T1). Then, it is examined how many of the vehicles that have passed the downstream point are associated with the vehicles that have passed the upstream point. This ratio is called the matching rate. For example, out of m vehicles that have passed the downstream point, if the p vehicles correspond to the vehicles that have passed the upstream point, the matching rate will be p / m. This matching rate is compared with a threshold value.
[0055]
This threshold value records the matching rate data before and after the sudden occurrence of the sudden event on the road, and the occurrence of the sudden event on the road can be detected with the highest accuracy by implementing the present invention. Choose a value like this. In addition, data on lane usage in various past conditions such as time of day, day of the week, day without event, etc. is accumulated, and the optimum threshold value is set according to time of day, day of week, presence of event, etc. You may make it set.
[0056]
In addition, measure the travel time and compare the threshold if the travel time is relatively short, i.e., close to free flow, and the threshold is relatively small, if the travel time is relatively long, i.e. traffic jam (Steps T2 to T4). Instead of travel time, it may be determined whether there is a traffic jam based on the traffic volume and the occupation rate.
When it is close to a free flow, the matching rate is relatively low even during normal times when no sudden events occur. Therefore, there is a high possibility of erroneous detection unless the threshold is lowered. On the other hand, during traffic jams, the matching rate is relatively high even during normal times. Therefore, if the threshold value is not raised, detection omissions increase.
[0057]
Although the increase / decrease of the threshold value in steps T2 to T4 may be set artificially, it is desirable to automatically perform it for labor saving.
The abnormality determination unit 24 compares the matching rate with the threshold value (step T5), and if lower than the threshold value, determines that a sudden event has occurred between the upstream and downstream points (step T7). If it is higher than the threshold, it is further checked whether the matching rate obtained by the correspondence of the vehicle that has passed the upstream and downstream points in the past (for example, one time before) is higher than the threshold (step T6). If there is no abnormality. If it is low, it is determined that the sudden event continues.
[0058]
As described above, when the matching rate is continuously higher than the threshold value twice or more, it is determined that there is no abnormality in order to avoid an erroneous determination in the case of accidental matching even if a sudden event occurs.
The occurrence of the sudden event described above may be determined in a plurality of sections. In this case, the matching rates in the respective sections are compared, and the section having the lowest matching ratio can be specified as the sudden event occurrence section.
[0059]
FIG. 9 is a flowchart for explaining the process of identifying the sudden event occurrence section.
First, the sudden event occurrence determination process described so far is performed in each of the monitoring target road sections 1, 2,..., I,. If the same processing is completed in all the monitoring target road sections 1, 2,..., I (YES in step W2), it is checked whether there is a section determined to have a sudden event (step W3). Then, the matching rates calculated in each section are compared (step W4). The section where the matching rate is minimum is specified as the sudden event occurrence section (step W5).
[0060]
Hereinafter, the reciprocal of the matching rate is referred to as “evaluation value”. That is, evaluation value = 1 / (matching rate).
FIG. 10 is a graph showing temporal transition of evaluation values obtained from detection processing results in five sections. According to this graph, the accident occurred at 8:20, and the evaluation values in the sections 1 to 3 increased. In particular, since the evaluation value of section 2 is the maximum, section 2 can be specified as the sudden event occurrence section.
[0061]
When the occurrence of the sudden event and its section are determined as described above, the traffic management center 10 displays the occurrence of the sudden event on the variable display boards 6 and 9, and the sudden event is detected in the vehicle through the roadside beacon 7. Notify the occurrence.
In this notification, the evaluation value is compared with a plurality of threshold values. One is a “detection threshold” and the other is a “caution threshold”. There is a relationship of “detection threshold value”> “caution threshold value”.
[0062]
If the evaluation value exceeds the detection threshold, the occurrence likelihood of the sudden event is sufficiently high, and it is determined that “the sudden event has occurred”. If this detection threshold is too high, detection omissions increase, and if the detection threshold is too low, false detections increase. This detection threshold value may be automatically determined based on the results of the detection omission rate and the false detection rate.
If the detection threshold is not exceeded, this evaluation value is compared with the attention threshold. If the attention threshold value is exceeded, it is determined that the likelihood of occurrence of a sudden event is moderately high and the “attention state where the possibility of a sudden event is high” is determined.
[0063]
If the caution threshold is not exceeded, the occurrence likelihood of the sudden event is low, and it is determined that “no sudden event has occurred”.
If it is determined that “sudden event has occurred”, the output processing unit 25 of the traffic management center 10 displays a message giving a driver warning such as “Accident / Stop” on the variable display boards 6 and 9, The vehicle is also notified through the roadside beacon 7 that it is a dangerous zone.
[0064]
If it is determined that the “attention state with a high possibility of occurrence of a sudden event”, the output processing unit 25 alerts the driver to the variable display boards 6 and 9 like “attention ahead”. Is displayed, and the vehicle is also notified through the roadside beacon 7 that it is a travel attention section.
Then, the information is communicated to the related organization 13 and the broadcasting station 14 through a communication line.
[0065]
If road construction or the like is already planned and an abnormal traffic flow is predicted, the output processing unit 25 may determine whether the sudden event has occurred at the time, but based on this determination, the variable display board 6 , 9 are not displayed, and the related organizations 13 and broadcast stations 14 are not displayed.
Although the embodiment of the present invention has been described above, the implementation of the present invention is not limited to the above. In the above example, an expressway is assumed, but it may be a general road. Although a road with two lanes is assumed, the number of lanes is not limited to two, and may be one lane or three or more lanes.
[0066]
Further, instead of the plurality of embedded vehicle sensors 5, a Doppler vehicle sensor installed on the side of the road may be used. Alternatively, a television camera may be installed on the road to detect the number of passing vehicles, the vehicle height, the vehicle length, the passing speed, etc. by image processing.
Further, other known methods may be employed as a method for calculating the matching rate. For example, a method of taking an image of a vehicle and recognizing the characteristics of the vehicle, such as color and plate number, using image processing may be employed.
[0067]
【The invention's effect】
As described above, according to the traffic flow abnormality detection device of the present invention, it is possible to accurately detect the occurrence of a sudden event on a road.
[Brief description of the drawings]
FIG. 1 is a schematic diagram showing a traffic flow monitoring system for detecting an abnormality in traffic flow.
FIG. 2 is a functional block diagram of the computer 11 of the traffic management center 10;
FIG. 3 is a flowchart for explaining a vehicle group matching processing method performed by a matching determination unit 22;
FIG. 4 is a diagram depicting a two-dimensional grid-like directed graph.
FIG. 5 is a diagram of a two-dimensional grid-like directed graph for showing the result of solving the longest path problem with n = 3 and m = 4.
FIG. 6 is a two-dimensional grid-like directed graph when n = 4 and m = 3 and only the vehicle b4 is not matched.
FIG. 7 is a diagram depicting a two-dimensional grid-like directed graph for explaining an algorithm that does not require an external gap on the time series latest time point side.
FIG. 8 is a flowchart for explaining processing for monitoring occurrence of sudden events performed by the abnormality determination unit 24;
FIG. 9 is a flowchart for explaining a process for specifying a sudden event occurrence section;
FIG. 10 is a graph showing temporal transition of evaluation values obtained from detection processing results in five sections.
[Explanation of symbols]
DESCRIPTION OF SYMBOLS 1 Expressway 2 General road 3 Vehicle detector 4 Primary processing device 5 Vehicle detector 6 Variable display board 7 Roadside beacon 9 Variable display board 10 Traffic management center 11 Computer 13 Related organization 14 Broadcasting station 22 Matching judgment part 24 Abnormality judgment part

Claims (11)

Vehicle feature quantity observation means installed at a plurality of vehicle observation points and observing feature quantities of passing vehicles;
Matching determination means for determining the degree of coincidence of the arrangement of vehicle groups by associating vehicles that have passed through each vehicle observation point;
An abnormality determining means for detecting the occurrence of a sudden event on the road between the vehicle observation points when the degree of coincidence of the arrangement of the vehicle group becomes smaller than a threshold based on the determination result of the matching determining means; An apparatus for detecting an abnormality in a traffic flow, comprising:   The traffic flow abnormality detection device according to claim 1, wherein the vehicle feature amount observation means observes a vehicle length.   The traffic flow abnormality detection device according to claim 1, wherein the vehicle feature amount observation means observes a vehicle height.   The traffic flow abnormality detection device according to claim 1, wherein the vehicle feature amount observing means captures an image of the vehicle. The threshold is times, days, prompts such statistically in accordance with the presence or absence of special events, the abnormality detection apparatus according to claim 1, wherein the traffic flow is stored values. The threshold value is automatically determined according to the traffic conditions, the abnormality detection apparatus according to claim 1, wherein the traffic flow is stored values. 2. The traffic flow abnormality detecting device according to claim 1, further comprising information providing means for notifying the outside of the occurrence of the sudden event when a sudden event on the road is detected by the abnormality determining means . The information providing means provides information to a vehicle traveling in the area or the section or a vehicle expected to travel into the area or the section. Item 8. The traffic flow abnormality detection device according to Item 7 . The abnormality determining means performs stepwise determination according to the magnitude of the evaluation value that is the basis of the determination, and the information providing means determines the content of the abnormality information according to the result of the stepwise determination by the abnormality determining means. The traffic flow abnormality detection device according to claim 7, wherein: The abnormality determination unit, when detecting an abnormality in a traffic flow in a plurality of road sections, identifies an abnormality occurrence section according to a magnitude of an evaluation value that is a basis of determination. Traffic flow anomaly detection device. Measure vehicles traveling on the road at multiple vehicle observation points,
Based on this measurement result, the feature quantity of the passing vehicle is observed,
When the degree of coincidence of the arrangement of the vehicle group is determined by associating the vehicles that have passed through the respective vehicle observation points based on the feature amount, and the degree of coincidence of the arrangement of the vehicle group becomes smaller than a threshold value In addition, a traffic flow abnormality detection method characterized by detecting the occurrence of a sudden event on a road between vehicle observation points .

Images